{"authorId": "1741101", "url": "https://www.semanticscholar.org/author/1741101", "papers": [{"paperId": "cb92a7f9d9dbcf9145e32fdfa0e70e2a6b828eb1", "title": "The Semantic Scholar Open Data Platform", "openAccessPdf": {"url": "http://arxiv.org/pdf/2301.10140", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/2301.10140, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "143967880", "name": "Rodney Michael Kinney"}, {"authorId": "1667818755", "name": "Chloe Anastasiades"}, {"authorId": "2202417686", "name": "Russell Authur"}, {"authorId": "46181066", "name": "Iz Beltagy"}, {"authorId": "2699105", "name": "Jonathan Bragg"}, {"authorId": "2202412440", "name": "Alexandra Buraczynski"}, {"authorId": "51199773", "name": "Isabel Cachola"}, {"authorId": "2202412446", "name": "Stefan Candra"}, {"authorId": "1648642525", "name": "Yoganand Chandrasekhar"}, {"authorId": "2527954", "name": "Arman Cohan"}, {"authorId": "46230609", "name": "Miles Crawford"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "38092776", "name": "Jason Dunkelberger"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "79519990", "name": "Rob Evans"}, {"authorId": "46411828", "name": "Sergey Feldman"}, {"authorId": "2202417961", "name": "Joseph Gorney"}, {"authorId": "2052859168", "name": "David W. Graham"}, {"authorId": "2200023814", "name": "F.Q. Hu"}, {"authorId": "153179615", "name": "Regan Huff"}, {"authorId": "145104486", "name": "Daniel King"}, {"authorId": "41018147", "name": "Sebastian Kohlmeier"}, {"authorId": "2003338023", "name": "Bailey Kuehl"}, {"authorId": "48758753", "name": "Michael Langan"}, {"authorId": "2116442078", "name": "Daniel Lin"}, {"authorId": "2143857321", "name": "Haokun Liu"}, {"authorId": "46258841", "name": "Kyle Lo"}, {"authorId": "3047023", "name": "Jaron Lochner"}, {"authorId": "2071601396", "name": "Kelsey MacMillan"}, {"authorId": "144240185", "name": "Tyler C. Murray"}, {"authorId": "145541350", "name": "Christopher Newell"}, {"authorId": "2115660042", "name": "Smita Rao"}, {"authorId": "40408676", "name": "Shaurya Rohatgi"}, {"authorId": "114609552", "name": "Paul Sayre"}, {"authorId": "101568984", "name": "Shannon Zejiang Shen"}, {"authorId": "2116287642", "name": "Amanpreet Singh"}, {"authorId": "3328733", "name": "Luca Soldaini"}, {"authorId": "48813613", "name": "Shivashankar Subramanian"}, {"authorId": "2125122431", "name": "A. Tanaka"}, {"authorId": "1860983", "name": "Alex D Wade"}, {"authorId": "82676859", "name": "Linda M. Wagner"}, {"authorId": "31860505", "name": "Lucy Lu Wang"}, {"authorId": "46212260", "name": "Christopher Wilhelm"}, {"authorId": "2109360564", "name": "Caroline Wu"}, {"authorId": "82148460", "name": "Jiangjiang Yang"}, {"authorId": "98442688", "name": "Angele Zamarron"}, {"authorId": "15292561", "name": "Madeleine van Zuylen"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": "The volume of scientific output is creating an urgent need for automated tools to help scientists keep up with developments in their field. Semantic Scholar (S2) is an open data platform and website aimed at accelerating science by helping scholars discover and understand scientific literature. We combine public and proprietary data sources using state-of-theart techniques for scholarly PDF content extraction and automatic knowledge graph construction to build the Semantic Scholar Academic Graph, the largest open scientific literature graph to-date, with 200M+ papers, 80M+ authors, 550M+ paper-authorship edges, and 2.4B+ citation edges. The graph includes advanced semantic features such as structurally parsed text, natural language summaries, and vector embeddings. In this paper, we describe the components of the S2 data processing pipeline and the associated APIs offered by the platform. We will update this living document to reflect changes as we add new data offerings and improve existing services."}, {"paperId": "6c5c6f883604a3abaa829b83d2958de8c343beeb", "title": "A Computational Inflection for Scientific Discovery", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/2205.02007, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2041698667", "name": "Tom Hope"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "145479841", "name": "E. Horvitz"}], "abstract": "Enabling researchers to leverage systems to overcome the limits of human cognitive capacity."}, {"paperId": "b4916c497d996ad21433a8fda701b6306b0854cd", "title": "Artificial Intelligence and Life in 2030: The One Hundred Year Study on Artificial Intelligence", "openAccessPdf": {"url": "https://arxiv.org/pdf/2211.06318", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/2211.06318, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144848112", "name": "P. Stone"}, {"authorId": "72419159", "name": "R. Brooks"}, {"authorId": "2841157", "name": "Erik Brynjolfsson"}, {"authorId": "3014341", "name": "Ryan Calo"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2942743", "name": "G. Hager"}, {"authorId": "144049352", "name": "Julia Hirschberg"}, {"authorId": "3027736", "name": "Shivaram Kalyanakrishnan"}, {"authorId": "1783184", "name": "Ece Kamar"}, {"authorId": "1691597", "name": "Sarit Kraus"}, {"authorId": "1388404060", "name": "Kevin Leyton-Brown"}, {"authorId": "30907562", "name": "D. Parkes"}, {"authorId": "81619738", "name": "W. Press"}, {"authorId": "98622177", "name": "A. Saxenian"}, {"authorId": "143873972", "name": "J. Shah"}, {"authorId": "143736701", "name": "Milind Tambe"}, {"authorId": "2862181", "name": "Astro Teller"}], "abstract": "In September 2016, Stanford's\"One Hundred Year Study on Artificial Intelligence\"project (AI100) issued the first report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 17 study authors, each of whom is deeply rooted in AI research, chaired by Peter Stone of the University of Texas at Austin. The report, entitled\"Artificial Intelligence and Life in 2030,\"examines eight domains of typical urban settings on which AI is likely to have impact over the coming years: transportation, home and service robots, healthcare, education, public safety and security, low-resource communities, employment and workplace, and entertainment. It aims to provide the general public with a scientifically and technologically accurate portrayal of the current state of AI and its potential and to help guide decisions in industry and governments, as well as to inform research and development in the field. The charge for this report was given to the panel by the AI100 Standing Committee, chaired by Barbara Grosz of Harvard University."}, {"paperId": "d49cf805bcef60f206bca60d7315f6e52217b44f", "title": "Infrastructure for Rapid Open Knowledge Network Development", "openAccessPdf": {"url": "https://ojs.aaai.org/index.php/aimagazine/article/download/19126/18895", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v43i1.19126?email= or https://doi.org/10.1609/aimag.v43i1.19126, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "47393354", "name": "Michael R. Anderson"}, {"authorId": "46181066", "name": "Iz Beltagy"}, {"authorId": "1962331387", "name": "Arie Cattan"}, {"authorId": "2357280073", "name": "Sarah E. Chasins"}, {"authorId": "7465342", "name": "Ido Dagan"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "46411828", "name": "Sergey Feldman"}, {"authorId": "2162713295", "name": "Tian Gao"}, {"authorId": "2041698667", "name": "Tom Hope"}, {"authorId": "2112441120", "name": "Kexin Huang"}, {"authorId": "1406046265", "name": "Sophie Johnson"}, {"authorId": "145104486", "name": "Daniel King"}, {"authorId": "46258841", "name": "Kyle Lo"}, {"authorId": "143904011", "name": "Yuze Lou"}, {"authorId": "2072726795", "name": "M. Shapiro"}, {"authorId": "2162680951", "name": "Dinghao Shen"}, {"authorId": "48813613", "name": "Shivashankar Subramanian"}, {"authorId": "31860505", "name": "Lucy Lu Wang"}, {"authorId": "2107925083", "name": "Yuning Wang"}, {"authorId": "2165313960", "name": "Yitong Wang"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "1486207884", "name": "Jenny M. Vo-Phamhi"}, {"authorId": "2162674366", "name": "Anna Zeng"}, {"authorId": "47114531", "name": "Jiayun Zou"}], "abstract": "The past decade has witnessed a growth in the use of knowledge graph technologies for advanced data search, data integration, and query-answering applications. The leading example of a public, general-purpose open knowledge network (aka\u00a0knowledge graph) is Wikidata, which has demonstrated remarkable advances in quality and coverage over this time. Proprietary knowledge graphs drive some of the leading applications of the day including, for example, Google Search, Alexa, Siri, and Cortana. Open Knowledge Networks are exciting: they promise the power of structured database-like queries with the potential for the wide coverage that is today only provided by the Web. With the current state of the art, building, using, and scaling large knowledge networks can still be frustratingly slow. This article describes a National Science Foundation Convergence Accelerator project to build a set of Knowledge Network Programming Infrastructure systems to address this\u00a0issue."}, {"paperId": "116c1cf1650648d85405209849816cb6e0b8a13f", "title": "Can Virtual Communities Be Real?", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.2307/J.CTV19FVXXK.8?email= or https://doi.org/10.2307/J.CTV19FVXXK.8, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "507a7a2946e449faa9bc9a4ea9076f80b131cdc9", "title": "Delphi: Towards Machine Ethics and Norms", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2112504145", "name": "Liwei Jiang"}, {"authorId": "2012510", "name": "Jena D. Hwang"}, {"authorId": "1857797", "name": "Chandra Bhagavatula"}, {"authorId": "39227408", "name": "Ronan Le Bras"}, {"authorId": "39191185", "name": "Maxwell Forbes"}, {"authorId": "32196774", "name": "Jon Borchardt"}, {"authorId": "50685571", "name": "Jenny T Liang"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2729164", "name": "Maarten Sap"}, {"authorId": "1699545", "name": "Yejin Choi"}], "abstract": null}, {"paperId": "6e5170901d940be61248de0537cda57491f6a045", "title": "Next Big Challenges in Core AI Technology", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/978-3-030-69128-8_7?email= or https://doi.org/10.1007/978-3-030-69128-8_7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145279674", "name": "A. Dengel"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2080048148", "name": "Nicole DeCario"}, {"authorId": "2470869", "name": "H. Hoos"}, {"authorId": "48004138", "name": "Li Fei-Fei"}, {"authorId": "1737901", "name": "Junichi Tsujii"}, {"authorId": "145919532", "name": "P. Traverso"}], "abstract": null}, {"paperId": "e3d5d70005bcc9d36dc84a969b92e6f7518defa9", "title": "Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text", "openAccessPdf": {"url": "https://aclanthology.org/2021.emnlp-main.141.pdf", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/2112.00800, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "143997772", "name": "Christopher Clark"}, {"authorId": "145704057", "name": "J. Salvador"}, {"authorId": "34846449", "name": "Dustin Schwenk"}, {"authorId": "1394856873", "name": "Derrick Bonafilia"}, {"authorId": "2064210", "name": "Mark Yatskar"}, {"authorId": "3386570", "name": "Eric Kolve"}, {"authorId": "3360135", "name": "Alvaro Herrasti"}, {"authorId": "2112287145", "name": "Jonghyun Choi"}, {"authorId": "151493135", "name": "Sachin Mehta"}, {"authorId": "46181683", "name": "Sam Skjonsberg"}, {"authorId": "3393851", "name": "Carissa Schoenick"}, {"authorId": "35429963", "name": "Aaron Sarnat"}, {"authorId": "2548384", "name": "Hannaneh Hajishirzi"}, {"authorId": "2684226", "name": "Aniruddha Kembhavi"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "143787583", "name": "Ali Farhadi"}], "abstract": "Communicating with humans is challenging for AIs because it requires a shared understanding of the world, complex semantics (e.g., metaphors or analogies), and at times multi-modal gestures (e.g., pointing with a finger, or an arrow in a diagram). We investigate these challenges in the context of Iconary, a collaborative game of drawing and guessing based on Pictionary, that poses a novel challenge for the research community. In Iconary, a Guesser tries to identify a phrase that a Drawer is drawing by composing icons, and the Drawer iteratively revises the drawing to help the Guesser in response. This back-and-forth often uses canonical scenes, visual metaphor, or icon compositions to express challenging words, making it an ideal test for mixing language and visual/symbolic communication in AI. We propose models to play Iconary and train them on over 55,000 games between human players. Our models are skillful players and are able to employ world knowledge in language models to play with words unseen during training."}, {"paperId": "2eab8dd8db899437570c5d61a6434b4ba575f768", "title": "Semantic Scholar, NLP, and the Fight against COVID-19", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/3412815.3416880?email= or https://doi.org/10.1145/3412815.3416880, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "This talk will describe the dramatic creation of the COVID-19 Open Research Dataset (CORD-19) at the Allen Institute for AI and the broad range of efforts, both inside and outside of the Semantic Scholar project, to garner insights into COVID-19 and its treatment based on this data. The talk will highlight the difficult problems facing the emerging field of Scientific Language Processing."}, {"paperId": "63f5febc710a2e3222f7ebe6ef1b7a5af3874185", "title": "Green AI", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2279023325", "name": "Roy Schwartz"}, {"authorId": "34176020", "name": "Jesse Dodge"}, {"authorId": "144365875", "name": "Noah A. Smith"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "bc411487f305e451d7485e53202ec241fcc97d3b", "title": "CORD-19: The Covid-19 Open Research Dataset", "openAccessPdf": {"url": "", "status": null, "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/2004.10706, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "31860505", "name": "Lucy Lu Wang"}, {"authorId": "46258841", "name": "Kyle Lo"}, {"authorId": "1648642525", "name": "Yoganand Chandrasekhar"}, {"authorId": "65983884", "name": "Russell Reas"}, {"authorId": "82148460", "name": "Jiangjiang Yang"}, {"authorId": "40329918", "name": "Darrin Eide"}, {"authorId": "37996742", "name": "Kathryn Funk"}, {"authorId": "2208580", "name": "Yannis Katsis"}, {"authorId": "143967880", "name": "Rodney Michael Kinney"}, {"authorId": "2145253428", "name": "Ziyang Liu"}, {"authorId": "143696607", "name": "William Merrill"}, {"authorId": "115392299", "name": "P. Mooney"}, {"authorId": "69437054", "name": "D. Murdick"}, {"authorId": "1453742562", "name": "Devvret Rishi"}, {"authorId": "2055678827", "name": "J. Sheehan"}, {"authorId": "3303634", "name": "Zhihong Shen"}, {"authorId": "1405473759", "name": "Brandon Stilson"}, {"authorId": "1860983", "name": "Alex D Wade"}, {"authorId": "1748169", "name": "Kuansan Wang"}, {"authorId": "46212260", "name": "Christopher Wilhelm"}, {"authorId": "2064542611", "name": "Boya Xie"}, {"authorId": "21811471", "name": "Douglas A. Raymond"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "41018147", "name": "Sebastian Kohlmeier"}], "abstract": "The COVID-19 Open Research Dataset (CORD-19) is a growing resource of scientific papers on COVID-19 and related historical coronavirus research. CORD-19 is designed to facilitate the development of text mining and information retrieval systems over its rich collection of metadata and structured full text papers. Since its release, CORD-19 has been downloaded over 200K times and has served as the basis of many COVID-19 text mining and discovery systems. In this article, we describe the mechanics of dataset construction, highlighting challenges and key design decisions, provide an overview of how CORD-19 has been used, and describe several shared tasks built around the dataset. We hope this resource will continue to bring together the computing community, biomedical experts, and policy makers in the search for effective treatments and management policies for COVID-19."}, {"paperId": "007bc04c97f9f8bcec0487699e197315418f22e7", "title": "From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project", "openAccessPdf": {"url": "https://ojs.aaai.org/aimagazine/index.php/aimagazine/article/download/5304/14933", "status": "GREEN", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1909.01958, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1783281", "name": "Daniel Khashabi"}, {"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "40135250", "name": "Bhavana Dalvi"}, {"authorId": "46666605", "name": "Kyle Richardson"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "3393851", "name": "Carissa Schoenick"}, {"authorId": "3385516", "name": "Oyvind Tafjord"}, {"authorId": "1721168", "name": "Niket Tandon"}, {"authorId": "3458824", "name": "Sumithra Bhakthavatsalam"}, {"authorId": "3458736", "name": "Dirk Groeneveld"}, {"authorId": "1983252", "name": "Michal Guerquin"}, {"authorId": "144874222", "name": "Michael Schmitz"}], "abstract": "\n \n \nAI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even as recently as 2016, the best AI system could achieve merely 59.3 percent on an 8th grade science exam. This article reports success on the Grade 8 New York Regents Science Exam, where for the first time a system scores more than 90 percent on the exam\u2019s nondiagram, multiple choice (NDMC) questions. In addition, our Aristo system, building upon the success of recent language models, exceeded 83 percent on the corresponding Grade 12 Science Exam NDMC questions. The results, on unseen test questions, are robust across different test years and different variations of this kind of test. They demonstrate that modern natural language processing methods can result in mastery on this task. While not a full solution to general question-answering (the questions are limited to 8th grade multiple-choice science) it represents a significant milestone for the field. \n \n \n"}, {"paperId": "3c5f1ab37f70db503636075e15b3173f86eea00b", "title": "Green AI", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1907.10597, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "4671928", "name": "Roy Schwartz"}, {"authorId": "34176020", "name": "Jesse Dodge"}, {"authorId": "144365875", "name": "Noah A. Smith"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "The computations required for deep learning research have been doubling every few months, resulting in an estimated 300,000x increase from 2012 to 2018 [2]. These computations have a surprisingly large carbon footprint [38]. Ironically, deep learning was inspired by the human brain, which is remarkably energy efficient. Moreover, the financial cost of the computations can make it difficult for academics, students, and researchers, in particular those from emerging economies, to engage in deep learning research. This position paper advocates a practical solution by making efficiency an evaluation criterion for research alongside accuracy and related measures. In addition, we propose reporting the financial cost or\"price tag\"of developing, training, and running models to provide baselines for the investigation of increasingly efficient methods. Our goal is to make AI both greener and more inclusive---enabling any inspired undergraduate with a laptop to write high-quality research papers. Green AI is an emerging focus at the Allen Institute for AI."}, {"paperId": "637a4dd4ce58cba58e921f927aa1e96b3fb6bdea", "title": "Quantifying Sex Bias in Clinical Studies at Scale With Automated Data Extraction", "openAccessPdf": {"url": "https://jamanetwork.com/journals/jamanetworkopen/articlepdf/2737103/feldman_2019_oi_190268.pdf", "status": "GOLD", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://pmc.ncbi.nlm.nih.gov/articles/PMC6613296, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "46411828", "name": "Sergey Feldman"}, {"authorId": "145585097", "name": "Bridger Waleed Ammar"}, {"authorId": "46258841", "name": "Kyle Lo"}, {"authorId": "5076824", "name": "E. Trepman"}, {"authorId": "15292561", "name": "Madeleine van Zuylen"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Key Points Question What is the magnitude of female underrepresentation in clinical studies? Findings In this cross-sectional study, machine reading to extract sex data from 43\u2009135 published articles and 13\u2009165 clinical trial records showed substantial underrepresentation of female participants, with studies as measurement unit, in 7 of 11 disease categories, especially HIV/AIDS, chronic kidney diseases, and cardiovascular diseases. Sex bias in articles for all categories combined was unchanged over time with studies as the measurement unit but improved with participants as measurement unit. Meaning This study suggests that sex bias against female participants in clinical studies persists, but results differ when studies vs participants are the measurement units."}, {"paperId": "7d8f8d676daec2388196c567881ade84ce3c05dc", "title": "Green AI", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "4671928", "name": "Roy Schwartz"}, {"authorId": "34176020", "name": "Jesse Dodge"}, {"authorId": "144365875", "name": "Noah A. Smith"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "a197dc7522800487601525359f5d25efa09daf3d", "title": "Gender trends in computer science authorship", "openAccessPdf": {"url": "https://arxiv.org/pdf/1906.07883", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1906.07883, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "31860505", "name": "Lucy Lu Wang"}, {"authorId": "2157025", "name": "Gabriel Stanovsky"}, {"authorId": "20745881", "name": "Luca Weihs"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Under optimistic projection models, gender parity is forecast to be reached after 2100."}, {"paperId": "10155d9b4ff9f99d314e76d1ce71e33e3c089717", "title": "Technical perspective: Breaking the mold of machine learning", "openAccessPdf": {"url": "http://dl.acm.org/ft_gateway.cfm?id=3191511&type=pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/3191511?email= or https://doi.org/10.1145/3191511, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "28244d50e085fb91b96749ff84101387f2a83d4d", "title": "Point: Should AI technology be regulated?", "openAccessPdf": {"url": "http://dl.acm.org/ft_gateway.cfm?id=3197382&type=pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/3197382?email= or https://doi.org/10.1145/3197382, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Considering the difficult technical and sociological issues affecting the regulation of artificial intelligence research and applications."}, {"paperId": "649def34f8be52c8b66281af98ae884c09aef38b", "title": "Construction of the Literature Graph in Semantic Scholar", "openAccessPdf": {"url": "https://www.aclweb.org/anthology/N18-3011.pdf", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1805.02262, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145585097", "name": "Bridger Waleed Ammar"}, {"authorId": "3458736", "name": "Dirk Groeneveld"}, {"authorId": "1857797", "name": "Chandra Bhagavatula"}, {"authorId": "46181066", "name": "Iz Beltagy"}, {"authorId": "46230609", "name": "Miles Crawford"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "38092776", "name": "Jason Dunkelberger"}, {"authorId": "143718836", "name": "Ahmed Elgohary"}, {"authorId": "46411828", "name": "Sergey Feldman"}, {"authorId": "4480314", "name": "Vu A. Ha"}, {"authorId": "143967880", "name": "Rodney Michael Kinney"}, {"authorId": "41018147", "name": "Sebastian Kohlmeier"}, {"authorId": "46258841", "name": "Kyle Lo"}, {"authorId": "144240185", "name": "Tyler C. Murray"}, {"authorId": "46256862", "name": "Hsu-Han Ooi"}, {"authorId": "39139825", "name": "Matthew E. Peters"}, {"authorId": "39561369", "name": "Joanna L. Power"}, {"authorId": "46181683", "name": "Sam Skjonsberg"}, {"authorId": "31860505", "name": "Lucy Lu Wang"}, {"authorId": "46212260", "name": "Christopher Wilhelm"}, {"authorId": "2112339497", "name": "Zheng Yuan"}, {"authorId": "15292561", "name": "Madeleine van Zuylen"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "We describe a deployed scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery. The resulting literature graph consists of more than 280M nodes, representing papers, authors, entities and various interactions between them (e.g., authorships, citations, entity mentions). We reduce literature graph construction into familiar NLP tasks (e.g., entity extraction and linking), point out research challenges due to differences from standard formulations of these tasks, and report empirical results for each task. The methods described in this paper are used to enable semantic features in www.semanticscholar.org."}, {"paperId": "88bb0a28bb58d847183ec505dda89b63771bb495", "title": "Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1803.05457, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "3390191", "name": "Isaac Cowhey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "3393851", "name": "Carissa Schoenick"}, {"authorId": "3385516", "name": "Oyvind Tafjord"}], "abstract": "We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous challenges such as SQuAD or SNLI. The ARC question set is partitioned into a Challenge Set and an Easy Set, where the Challenge Set contains only questions answered incorrectly by both a retrieval-based algorithm and a word co-occurence algorithm. The dataset contains only natural, grade-school science questions (authored for human tests), and is the largest public-domain set of this kind (7,787 questions). We test several baselines on the Challenge Set, including leading neural models from the SQuAD and SNLI tasks, and find that none are able to significantly outperform a random baseline, reflecting the difficult nature of this task. We are also releasing the ARC Corpus, a corpus of 14M science sentences relevant to the task, and implementations of the three neural baseline models tested. Can your model perform better? We pose ARC as a challenge to the community."}, {"paperId": "3b411553dd5706f5376cc83ca0d4530936b6568e", "title": "UNESCO geopark: Stop ruining Turkey's geological heritage", "openAccessPdf": {"url": "https://digital.csic.es/bitstream/10261/327622/5/Clapham%20et%20al_2017.pdf", "status": "GREEN", "license": "CCBYNCND", "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1038/547032d?email= or https://doi.org/10.1038/547032d, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "6bed23ebd9998e85bad446b9a56ea53f463d0f8a", "title": "Learning to Predict Citation-Based Impact Measures", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.5555/3200334.3200341?email= or https://doi.org/10.5555/3200334.3200341, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "20745881", "name": "Luca Weihs"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Citations implicitly encode a community's judgment of a paper's importance and thus provide a unique signal by which to study scientific impact. Efforts in understanding and refining this signal are reflected in the probabilistic modeling of citation networks and the proliferation of citation-based impact measures such as Hirsch's h-index. While these efforts focus on understanding the past and present, they leave open the question of whether scientific impact can be predicted into the future. Recent work addressing this deficiency has employed linear and simple probabilistic models; we show that these results can be handily outperformed by leveraging non-linear techniques. In particular, we find that these AI methods can predict measures of scientific impact for papers and authors, namely citation rates and h-indices, with surprising accuracy, even 10 years into the future. Moreover, we demonstrate how existing probabilistic models for paper citations can be extended to better incorporate refined prior knowledge. While predictions of scientific impact should be approached with healthy skepticism, our results improve upon prior efforts and form a baseline against which future progress can be easily judged."}, {"paperId": "73f333994f5896ba368bfc1211dba1dabf993e21", "title": "Incorporating Ethics into Artificial Intelligence", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/s10892-017-9252-2?email= or https://doi.org/10.1007/s10892-017-9252-2, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8856fba1922b07082e08a61051f818c26554d0ce", "title": "Pros and Cons of Autonomous Weapons Systems", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "c08d482f5be1ab95a99d9527fdd5f5feb53c79c6", "title": "The ethics of robotic caregivers", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1075/IS.18.2.02ETZ?email= or https://doi.org/10.1075/IS.18.2.02ETZ, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "260f4a655a63e9f0e8867140a8797e7a64e0cdd2", "title": "Designing AI systems that obey our laws and values", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2955091?email= or https://doi.org/10.1145/2955091, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "390808617b277987999b6e8e0aa5742aab54a6a0", "title": "My Computer Is an Honor Student - but How Intelligent Is It? Standardized Tests as a Measure of AI", "openAccessPdf": {"url": "https://aaai.org/ojs/index.php/aimagazine/article/download/2636/2528", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v37i1.2636?email= or https://doi.org/10.1609/aimag.v37i1.2636, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "478b4a5123bd5fda98bb35e6317d7f3555fec97d", "title": "Combining Retrieval, Statistics, and Inference to Answer Elementary Science Questions", "openAccessPdf": {"url": "https://ojs.aaai.org/index.php/AAAI/article/download/10325/10184", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aaai.v30i1.10325?email= or https://doi.org/10.1609/aaai.v30i1.10325, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "3385516", "name": "Oyvind Tafjord"}, {"authorId": "1689647", "name": "Peter D. Turney"}, {"authorId": "1783281", "name": "Daniel Khashabi"}], "abstract": "\n \n What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results. We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only non-diagram, multiple choice questions), and show that our overall system\u2019s score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work. We conclude with a detailed analysis, illustrating the complementary strengths of each method in the ensemble. Our datasets are being released to enable further research.\n \n"}, {"paperId": "82756cad5045fedda3af23c4d6fe9ba90deafcc2", "title": "Keeping AI Legal", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.2139/SSRN.2726612?email= or https://doi.org/10.2139/SSRN.2726612, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "AI programs make numerous decisions on their own, lack transparency, and may change frequently. Hence, the article shows, unassisted human agents \u2014 such as auditors, accountants, inspectors, and police \u2014 cannot ensure that AI guided instruments will abide by the law. Human agents need assistance of AI oversight programs that analyze and oversee the operational AI programs. The article then asks whether operational AI programs should be programmed to enable human users to override them \u2014 without that such a move would undermine the legal order. The article next points out that AI operational programs provide very high surveillance capacities, and that hence AI oversight programs are essential for protecting individual rights in the cyber age. The article closes by discussing the argument that AI guided instruments, e.g. robots, lead to endangering much more than the legal order \u2014 that they may turn on their makers, or even destroy humanity."}, {"paperId": "8cc2d899876c50305c12a2c3bd2373ce561c46d6", "title": "Toward Automatic Bootstrapping of Online Communities Using Decision-theoretic Optimization", "openAccessPdf": {"url": "http://homes.cs.washington.edu/%7Ejbragg/files/huang-cscw16.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2818048.2820024?email= or https://doi.org/10.1145/2818048.2820024, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1979695", "name": "Shih-Wen Huang"}, {"authorId": "2699105", "name": "Jonathan Bragg"}, {"authorId": "3390191", "name": "Isaac Cowhey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "a5ae605457fd8c1c5cc2675417d44f8f59fc7c33", "title": "Question Answering via Integer Programming over Semi-Structured Knowledge", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1604.06076, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1783281", "name": "Daniel Khashabi"}, {"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144590225", "name": "Dan Roth"}], "abstract": "Answering science questions posed in natural language is an important AI challenge. Answering such questions often requires non-trivial inference and knowledge that goes beyond factoid retrieval. Yet, most systems for this task are based on relatively shallow Information Retrieval (IR) and statistical correlation techniques operating on large unstructured corpora. We propose a structured inference system for this task, formulated as an Integer Linear Program (ILP), that answers natural language questions using a semi-structured knowledge base derived from text, including questions requiring multi-step inference and a combination of multiple facts. On a dataset of real, unseen science questions, our system significantly outperforms (+14%) the best previous attempt at structured reasoning for this task, which used Markov Logic Networks (MLNs). It also improves upon a previous ILP formulation by 17.7%. When combined with unstructured inference methods, the ILP system significantly boosts overall performance (+10%). Finally, we show our approach is substantially more robust to a simple answer perturbation compared to statistical correlation methods."}, {"paperId": "afaae8591456819c58aaa9baafaeaaa8a9d972ff", "title": "Moving beyond the Turing Test with the Allen AI Science Challenge", "openAccessPdf": {"url": "https://arxiv.org/pdf/1604.04315", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1604.04315, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3393851", "name": "Carissa Schoenick"}, {"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "3385516", "name": "Oyvind Tafjord"}, {"authorId": "1689647", "name": "Peter D. Turney"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Answering questions correctly from standardized eighth-grade science tests is itself a test of machine intelligence."}, {"paperId": "b5930cecac0a64e2b1f2bc25f41b09bd949f7cea", "title": "IKE - An Interactive Tool for Knowledge Extraction", "openAccessPdf": {"url": "https://doi.org/10.18653/v1/w16-1303", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/W16-1303, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "40135250", "name": "Bhavana Dalvi"}, {"authorId": "3458824", "name": "Sumithra Bhakthavatsalam"}, {"authorId": "143997772", "name": "Christopher Clark"}, {"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38087946", "name": "Anthony Fader"}, {"authorId": "3458736", "name": "Dirk Groeneveld"}], "abstract": "Recent work on information extraction has suggested that fast, interactive tools can be highly effective; however, creating a usable system is challenging, and few publically available tools exist. In this paper we present IKE, a new extraction tool that performs fast, interactive bootstrapping to develop high-quality extraction patterns for targeted relations. Central to IKE is the notion that an extraction pattern can be treated as a search query over a corpus. To operationalize this, IKE uses a novel query language that is expressive, easy to understand, and fast to execute essential requirements for a practical system. It is also the first interactive extraction tool to seamlessly integrate symbolic (boolean) and distributional (similarity-based) methods for search. An initial evaluation suggests that relation tables can be populated substantially faster than by manual pattern authoring while retaining accuracy, and more reliably than fully automated tools, an important step towards practical KB construction. We are making IKE publically available (http://allenai.org/ software/interactive-knowledge-extraction)."}, {"paperId": "cb90d3732a50bce46165e75b2260e0c71a70ba33", "title": "AI assisted ethics", "openAccessPdf": {"url": "https://doi.org/10.1007/s10676-016-9400-6", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1007/s10676-016-9400-6?email= or https://doi.org/10.1007/s10676-016-9400-6, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "The growing number of \u2018smart\u2019 instruments, those equipped with AI, has raised concerns because these instruments make autonomous decisions; that is, they act beyond the guidelines provided them by programmers. Hence, the question the makers and users of smart instrument (e.g., driver-less cars) face is how to ensure that these instruments will not engage in unethical conduct (not to be conflated with illegal conduct). The article suggests that to proceed we need a new kind of AI program\u2014oversight programs\u2014that will monitor, audit, and hold operational AI programs accountable."}, {"paperId": "17230f5b3956188055a48c5f4f61d131cce0662f", "title": "Parsing Algebraic Word Problems into Equations", "openAccessPdf": {"url": "http://www.mitpressjournals.org/doi/pdf/10.1162/tacl_a_00160", "status": "GOLD", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/Q15-1042, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1403698986", "name": "Rik Koncel-Kedziorski"}, {"authorId": "2548384", "name": "Hannaneh Hajishirzi"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "29865576", "name": "S. Ang"}], "abstract": "This paper formalizes the problem of solving multi-sentence algebraic word problems as that of generating and scoring equation trees. We use integer linear programming to generate equation trees and score their likelihood by learning local and global discriminative models. These models are trained on a small set of word problems and their answers, without any manual annotation, in order to choose the equation that best matches the problem text. We refer to the overall system as Alges. We compare Alges with previous work and show that it covers the full gamut of arithmetic operations whereas Hosseini et al. (2014) only handle addition and subtraction. In addition, Alges overcomes the brittleness of the Kushman et al. (2014) approach on single-equation problems, yielding a 15% to 50% reduction in error."}, {"paperId": "1c7be3fc28296a97607d426f9168ad4836407e4b", "title": "Identifying Meaningful Citations", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "41222589", "name": "M. Valenzuela"}, {"authorId": "4480314", "name": "Vu A. Ha"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "7b49c59b2056308b01dcc495966d974e7c7741fc", "title": "The elephant in the room: getting value from Big Data", "openAccessPdf": {"url": "https://hal-imt.archives-ouvertes.fr/hal-01699868/file/webdb2015elephant.pdf", "status": "GREEN", "license": "other-oa", "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2767109.2770014?email= or https://doi.org/10.1145/2767109.2770014, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "69026873", "name": "S. Abiteboul"}, {"authorId": "145867172", "name": "X. Dong"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145860176", "name": "D. Srivastava"}, {"authorId": "1751591", "name": "G. Weikum"}, {"authorId": "1682824", "name": "J. Stoyanovich"}, {"authorId": "1679784", "name": "Fabian M. Suchanek"}], "abstract": null}, {"paperId": "c388c90413c7391bcef61e2aa4b5302cf6adf7b0", "title": "Exploring Markov Logic Networks for Question Answering", "openAccessPdf": {"url": "https://www.aclweb.org/anthology/D15-1080.pdf", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D15-1080, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "3053123", "name": "Eric Gribkoff"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Elementary-level science exams pose significant knowledge acquisition and reasoning challenges for automatic question answering. We develop a system that reasons with knowledge derived from textbooks, represented in a subset of firstorder logic. Automatic extraction, while scalable, often results in knowledge that is incomplete and noisy, motivating use of reasoning mechanisms that handle uncertainty. Markov Logic Networks (MLNs) seem a natural model for expressing such knowledge, but the exact way of leveraging MLNs is by no means obvious. We investigate three ways of applying MLNs to our task. First, we simply use the extracted science rules directly as MLN clauses and exploit the structure present in hard constraints to improve tractability. Second, we interpret science rules as describing prototypical entities, resulting in a drastically simplified but brittle network. Our third approach, called Praline, uses MLNs to align lexical elements as well as define and control how inference should be performed in this task. Praline demonstrates a 15% accuracy boost and a 10x reduction in runtime as compared to other MLNbased methods, and comparable accuracy to word-based baseline approaches."}, {"paperId": "c87dccf7c21e67679389f23f86f039cd96720c3f", "title": "Solving Geometry Problems: Combining Text and Diagram Interpretation", "openAccessPdf": {"url": "https://www.aclweb.org/anthology/D15-1171.pdf", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D15-1171, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "4418074", "name": "Minjoon Seo"}, {"authorId": "2548384", "name": "Hannaneh Hajishirzi"}, {"authorId": "143787583", "name": "Ali Farhadi"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "49269449", "name": "Clint Malcolm"}], "abstract": "This paper introduces GEOS, the first automated system to solve unaltered SAT geometry questions by combining text understanding and diagram interpretation. We model the problem of understanding geometry questions as submodular optimization, and identify a formal problem description likely to be compatible with both the question text and diagram. GEOS then feeds the description to a geometric solver that attempts to determine the correct answer. In our experiments, GEOS achieves a 49% score on official SAT questions, and a score of 61% on practice questions. 1 Finally, we show that by integrating textual and visual information, GEOS boosts the accuracy of dependency and semantic parsing of the question text."}, {"paperId": "e1d8f946ce3fa7725f37f417669ab79d00845360", "title": "Markov Logic Networks for Natural Language Question Answering", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1507.03045, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2236429", "name": "Tushar Khot"}, {"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "3053123", "name": "Eric Gribkoff"}, {"authorId": "48229640", "name": "Ashish Sabharwal"}, {"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Our goal is to answer elementary-level science questions using knowledge extracted automatically from science textbooks, expressed in a subset of first-order logic. Given the incomplete and noisy nature of these automatically extracted rules, Markov Logic Networks (MLNs) seem a natural model to use, but the exact way of leveraging MLNs is by no means obvious. We investigate three ways of applying MLNs to our task. In the first, we simply use the extracted science rules directly as MLN clauses. Unlike typical MLN applications, our domain has long and complex rules, leading to an unmanageable number of groundings. We exploit the structure present in hard constraints to improve tractability, but the formulation remains ineffective. In the second approach, we instead interpret science rules as describing prototypical entities, thus mapping rules directly to grounded MLN assertions, whose constants are then clustered using existing entity resolution methods. This drastically simplifies the network, but still suffers from brittleness. Finally, our third approach, called Praline, uses MLNs to align the lexical elements as well as define and control how inference should be performed in this task. Our experiments, demonstrating a 15\\% accuracy boost and a 10x reduction in runtime, suggest that the flexibility and different inference semantics of Praline are a better fit for the natural language question answering task."}, {"paperId": "24509d434a93d643a536bd87ece924e5e757fab1", "title": "The battle for the future of data mining", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2623330.2630816?email= or https://doi.org/10.1145/2623330.2630816, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Deep learning has catapulted to the front page of the New York Times, formed the core of the so-called 'Google brain', and achieved impressive results in vision, speech recognition, and elsewhere. Yet researchers have offered simple conundrums that deep learning doesn't address. For example, consider the sentence: 'The large ball crashed right through the table because it was made of Styrofoam.' What was made of Styrofoam? The large ball? Or the table? The answer is obviously 'the table', but if we change the word 'Styrofoam' to 'steel', the answer is clearly 'the large ball'. To automatically answer this type of question, our computers require an extensive body of knowledge. We believe that text mining can provide the requisite body of knowledge. My talk will describe work at the new Allen Institute for AI towards building the next-generation of text-mining systems."}, {"paperId": "2519ed73f8084b993664e5a0c240e2dd37ba7349", "title": "Diagram Understanding in Geometry Questions", "openAccessPdf": {"url": "https://ojs.aaai.org/index.php/AAAI/article/download/9146/9005", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aaai.v28i1.9146?email= or https://doi.org/10.1609/aaai.v28i1.9146, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "4418074", "name": "Minjoon Seo"}, {"authorId": "2548384", "name": "Hannaneh Hajishirzi"}, {"authorId": "143787583", "name": "Ali Farhadi"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "\n \n Automatically solving geometry questions is a long-standing AI problem. A geometry question typically includes a textual description accompanied by a diagram. The first step in solving geometry questions is diagram understanding, which consists of identifying visual elements in the diagram, their locations, their geometric properties, and aligning them to corresponding textual descriptions. In this paper, we present a method for diagram understanding that identifies visual elements in a diagram while maximizing agreement between textual and visual data. We show that the method's objective function is submodular; thus we are able to introduce an efficient method for diagram understanding that is close to optimal. To empirically evaluate our method, we compile a new dataset of geometry questions (textual descriptions and diagrams) and compare with baselines that utilize standard vision techniques. Our experimental evaluation shows an F1 boost of more than 17% in identifying visual elements and 25% in aligning visual elements with their textual descriptions.\n \n"}, {"paperId": "63da33e250e57a09dfe21545782d2ec6249bd62f", "title": "Chinese Open Relation Extraction for Knowledge Acquisition", "openAccessPdf": {"url": "https://doi.org/10.3115/v1/e14-4003", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/E14-4003, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "40130996", "name": "Yuen-Hsien Tseng"}, {"authorId": "1856962", "name": "Lung-Hao Lee"}, {"authorId": "2108361584", "name": "Shu-Yen Lin"}, {"authorId": "3229384", "name": "Bo-Shun Liao"}, {"authorId": "2152974289", "name": "Mei-Jun Liu"}, {"authorId": "153924342", "name": "Hsin-Hsi Chen"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38087946", "name": "Anthony Fader"}], "abstract": "This study presents the Chinese Open Relation Extraction (CORE) system that is able to extract entity-relation triples from Chinese free texts based on a series of NLP techniques, i.e., word segmentation, POS tagging, syntactic parsing, and extraction rules. We employ the proposed CORE techniques to extract more than 13 million entity-relations for an open domain question answering application. To our best knowledge, CORE is the first Chinese Open IE system for knowledge acquisition."}, {"paperId": "a1b19bb17697133a87e43c312f25f1e3ddd026cb", "title": "Unsupervised Methods for Determining Object and Relation Synonyms on the Web", "openAccessPdf": {"url": "https://jair.org/index.php/jair/article/download/10591/25338", "status": "GOLD", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://arxiv.org/abs/1401.5696, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3321874", "name": "A. Yates"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "The task of identifying synonymous relations and objects, or synonym resolution, is critical for high-quality information extraction. This paper investigates synonym resolution in the context of unsupervised information extraction, where neither hand-tagged training examples nor domain knowledge is available. The paper presents a scalable, fully-implemented system that runs in O(KN log N) time in the number of extractions, N, and the maximum number of synonyms per word, K. The system, called RESOLVER, introduces a probabilistic relational model for predicting whether two strings are co-referential based on the similarity of the assertions containing them. On a set of two million assertions extracted from the Web, RESOLVER resolves objects with 78% precision and 68% recall, and resolves relations with 90% precision and 35% recall. Several variations of RESOLVER's probabilistic model are explored, and experiments demonstrate that under appropriate conditions these variations can improve F1 by 5%. An extension to the basic RESOLVER system allows it to handle polysemous names with 97% precision and 95% recall on a data set from the TREC corpus."}, {"paperId": "a7862e14b4c20cefd6dc4f611f8aa866fabf130b", "title": "Learning to Solve Arithmetic Word Problems with Verb Categorization", "openAccessPdf": {"url": "https://aclanthology.org/D14-1058.pdf", "status": "HYBRID", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D14-1058, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "81007822", "name": "Mohammad Javad Hosseini"}, {"authorId": "2548384", "name": "Hannaneh Hajishirzi"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1684887", "name": "Nate Kushman"}], "abstract": "This paper presents a novel approach to learning to solve simple arithmetic word problems. Our system, ARIS, analyzes each of the sentences in the problem statement to identify the relevant variables and their values. ARIS then maps this information into an equation that represents the problem, and enables its (trivial) solution as shown in Figure 1. The paper analyzes the arithmetic-word problems \u201cgenre\u201d, identifying seven categories of verbs used in such problems. ARIS learns to categorize verbs with 81.2% accuracy, and is able to solve 77.7% of the problems in a corpus of standard primary school test questions. We report the first learning results on this task without reliance on predefined templates and make our data publicly available. 1"}, {"paperId": "ebfa37553df6ac9dc92a869417d0b394f2d3de25", "title": "A Data Scientist's Guide to Start-Ups", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1089/big.2014.0031?email= or https://doi.org/10.1089/big.2014.0031, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1752722", "name": "F. Provost"}, {"authorId": "1726660", "name": "Geoffrey I. Webb"}, {"authorId": "1988453", "name": "Ron Bekkerman"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1695784", "name": "U. Fayyad"}, {"authorId": "1933403", "name": "Claudia Perlich"}], "abstract": null}, {"paperId": "f86ec155cce6259e5230aaad3b762343757feb1d", "title": "Open question answering over curated and extracted knowledge bases", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2623330.2623677?email= or https://doi.org/10.1145/2623330.2623677, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "38087946", "name": "Anthony Fader"}, {"authorId": "1982950", "name": "Luke Zettlemoyer"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "2e50fa3360990aad1fc65a89231d16f8d3373836", "title": "Modeling Missing Data in Distant Supervision for Information Extraction", "openAccessPdf": {"url": "https://doi.org/10.1162/tacl_a_00234", "status": "GOLD", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/Q13-1030, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "1982950", "name": "Luke Zettlemoyer"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Distant supervision algorithms learn information extraction models given only large readily available databases and text collections. Most previous work has used heuristics for generating labeled data, for example assuming that facts not contained in the database are not mentioned in the text, and facts in the database must be mentioned at least once. In this paper, we propose a new latent-variable approach that models missing data. This provides a natural way to incorporate side information, for instance modeling the intuition that text will often mention rare entities which are likely to be missing in the database. Despite the added complexity introduced by reasoning about missing data, we demonstrate that a carefully designed local search approach to inference is very accurate and scales to large datasets. Experiments demonstrate improved performance for binary and unary relation extraction when compared to learning with heuristic labels, including on average a 27% increase in area under the precision recall curve in the binary case."}, {"paperId": "349df1e0b90bcb111757f323b3cc103f781fb347", "title": "Graph-based Methods for Natural Language Processing Introduction to Textgraphs-8 Jobimtext Visualizer: a Graph-based Approach to Contextualizing Distributional Similarity Reconstructing Big Semantic Similarity Networks from Global to Local Similarities: a Graph-based Contextualization Method Using D", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1714932", "name": "Zornitsa Kozareva"}, {"authorId": "2458509", "name": "Irina Matveeva"}, {"authorId": "50641517", "name": "Gabor Melli"}, {"authorId": "2256003", "name": "Vivi Nastase"}, {"authorId": "2158454997", "name": "Patricio Barco"}, {"authorId": "2143510401", "name": "Liang Huang"}, {"authorId": "40199896", "name": "Philippe Muller"}, {"authorId": "143927505", "name": "P. Sabatier"}, {"authorId": "2261699441", "name": "University"}, {"authorId": "2112055877", "name": "France"}, {"authorId": "143666773", "name": "R. Mu\u00f1oz"}, {"authorId": "1683562", "name": "Preslav Nakov"}, {"authorId": "103162089", "name": "Qatar Foundation"}, {"authorId": "2068519190", "name": "Roberto Navigli"}, {"authorId": "102661755", "name": "U. Sapienza"}, {"authorId": "2286022113", "name": "R. Di"}, {"authorId": "2055898897", "name": "Guenther Neumann"}, {"authorId": "38301933", "name": "Zaiqing Nie"}, {"authorId": "2029669151", "name": "Simone Paolo Ponzetto"}, {"authorId": "2158447838", "name": "Sapienza Universit\u00e0"}, {"authorId": "2158447852", "name": "Di Roma"}, {"authorId": "2059948993", "name": "Octavian Popescu"}, {"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2963586", "name": "Konstantin Voevodski"}, {"authorId": "72525354", "name": "Google"}, {"authorId": "2151036808", "name": "Rui Wang"}, {"authorId": "1391152289", "name": "Gmbh Dfki"}, {"authorId": "2146371556", "name": "Germany"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1829342", "name": "Christian Biemann"}, {"authorId": "39783117", "name": "Bonaventura Coppola"}, {"authorId": "46584153", "name": "Michael R. Glass"}, {"authorId": "1711133", "name": "A. Gliozzo"}, {"authorId": "9506522", "name": "Matthew Hatem"}, {"authorId": "144020368", "name": "Ailong He"}, {"authorId": "2109850299", "name": "Shefali Sharma"}, {"authorId": "2158447447", "name": "Chun-Nan"}, {"authorId": "3157001", "name": "Hakan Kardes"}, {"authorId": "3462278", "name": "Deepak Konidena"}, {"authorId": "2112401016", "name": "Siddharth Agrawal"}, {"authorId": "49993937", "name": "Micah Huff"}, {"authorId": "2879959", "name": "I. Kivim\u00e4ki"}, {"authorId": "144033941", "name": "Alexander Panchenko"}, {"authorId": "32294575", "name": "Adrien Dessy"}, {"authorId": "46852504", "name": "Dries Verdegem"}, {"authorId": "3103565", "name": "P. Francq"}, {"authorId": "2085466945", "name": "Hugues"}, {"authorId": "2858605", "name": "Martin Riedl"}, {"authorId": "3460518", "name": "Sumit Bhagwani"}, {"authorId": "3459874", "name": "Shrutiranjan Satapathy"}, {"authorId": "2376013", "name": "H. Karnick"}, {"authorId": "34607455", "name": "Chun-Nan Hsu"}, {"authorId": "35257737", "name": "Yo Ehara"}, {"authorId": "73355331", "name": "Issei Sato"}, {"authorId": "2835969", "name": "H. Oiwa"}, {"authorId": "153510134", "name": "H. Nakagawa"}, {"authorId": "3079821", "name": "Lakshmi Ramachandran"}, {"authorId": "51266460", "name": "ED Gehringer"}, {"authorId": "10022445", "name": "Ang Sun"}, {"authorId": "1775694", "name": "H. Bersini"}, {"authorId": "2356015", "name": "M. Saerens"}, {"authorId": "2472657", "name": "Goran Glavas"}, {"authorId": "143809437", "name": "J. \u0160najder"}], "abstract": null}, {"paperId": "3d4a123b8036f3bd81ad2659af69865cde404909", "title": "Towards Coherent Multi-Document Summarization", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/N13-1136, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "3db1c4f8d47840964153cbba93c60b7c07b56e75", "title": "Sound and E cient Closed-World Reasoning for Planning Technical Report 95-02-02", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "58c29ea020d9ac4799ed3fde17684a3a984a8e00", "title": "To buy or not to buy: that is the question", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2487575.2491129?email= or https://doi.org/10.1145/2487575.2491129, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "64c5453c6ef8a53a750bd2daa0b7b381caba2181", "title": "\u201c Out of the Box \u201d Information Extraction : a Case Study using Bio-Medical Texts", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2093554992", "name": "R. Bart"}], "abstract": null}, {"paperId": "c0be2ac2f45681f1852fc1d298af5dceb85834f4", "title": "Paraphrase-Driven Learning for Open Question Answering", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/P13-1158, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "38087946", "name": "Anthony Fader"}, {"authorId": "1982950", "name": "Luke Zettlemoyer"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "d43181fa9af5440360d4055e1ce7ddaaa6e82d77", "title": "Open Information Extraction to KBP Relations in 3 Hours", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "47819721", "name": "John Gilmer"}, {"authorId": "2093554992", "name": "R. Bart"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "f40219d81b785bddc7fdad9c2af2840af62661ae", "title": "Generating Coherent Event Schemas at Scale", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D13-1178, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Chambers and Jurafsky (2009) demonstrated that event schemas can be automatically induced from text corpora. However, our analysis of their schemas identifies several weaknesses, e.g., some schemas lack a common topic and distinct roles are incorrectly mixed into a single actor. It is due in part to their pair-wise representation that treats subjectverb independently from verb-object. This often leads to subject-verb-object triples that are not meaningful in the real-world. We present a novel approach to inducing open-domain event schemas that overcomes these limitations. Our approach uses cooccurrence statistics of semantically typed relational triples, which we call Rel-grams (relational n-grams). In a human evaluation, our schemas outperform Chambers\u2019s schemas by wide margins on several evaluation criteria. Both Rel-grams and event schemas are freely available to the research community."}, {"paperId": "3f6125032d63c06307f8cd9a0a3d3a79872f2956", "title": "Open Language Learning for Information Extraction (Author's Manuscript)", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "144874222", "name": "Michael Schmitz"}, {"authorId": "2093554992", "name": "R. Bart"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8ad0e78a9619c50bcb3cae4a589ec9a5d38c437c", "title": "Open Language Learning for Information Extraction", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/D12-1048, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2674444", "name": "Mausam"}, {"authorId": "144874222", "name": "Michael Schmitz"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2093554992", "name": "R. Bart"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "a5138880b9334f17a9bd35149d820ad96adc32f8", "title": "RevMiner: an extractive interface for navigating reviews on a smartphone", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2380116.2380120?email= or https://doi.org/10.1145/2380116.2380120, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "32065383", "name": "Jeff Huang"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1982950", "name": "Luke Zettlemoyer"}, {"authorId": "144358401", "name": "Kevin Clark"}, {"authorId": "2115446537", "name": "Christian Lee"}], "abstract": "Smartphones are convenient, but their small screens make searching, clicking, and reading awkward. Thus, perusing product reviews on a smartphone is difficult. In response, we introduce RevMiner - a novel smartphone interface that utilizes Natural Language Processing techniques to analyze and navigate reviews. RevMiner was run over 300K Yelp restaurant reviews extracting attribute-value pairs, where attributes represent restaurant attributes such as sushi and service, and values represent opinions about the attributes such as fresh or fast. These pairs were aggregated and used to: 1) answer queries such as \"cheap Indian food\", 2) concisely present information about each restaurant, and 3) identify similar restaurants. Our user studies demonstrate that on a smartphone, participants preferred RevMiner's interface to tag clouds and color bars, and that they preferred RevMiner's results to Yelp's, particularly for conjunctive queries (e.g., \"great food and huge portions\"). Demonstrations of RevMiner are available at revminer.com."}, {"paperId": "c5262730d8854f88106bdc204860ccf236b3345f", "title": "Open domain event extraction from twitter", "openAccessPdf": {"url": "http://turing.cs.washington.edu/papers/kdd12-ritter.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/2339530.2339704?email= or https://doi.org/10.1145/2339530.2339704, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "15173231", "name": "Sam Clark"}], "abstract": null}, {"paperId": "c5c08e6dec3bf8a036607593e11e389697e03f45", "title": "Entity Linking at Web Scale", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W12-3016, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "cffb556ee3d1e188f4688b71a8608bbe1883bc49", "title": "No Noun Phrase Left Behind: Detecting and Typing Unlinkable Entities", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/D12-1082, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e8bf81a8f46f5584351ce53c15846955ba45f327", "title": "Constructing a Textual KB from a Biology TextBook", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W12-3014, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "48323507", "name": "Peter Clark"}, {"authorId": "143878270", "name": "P. Harrison"}, {"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f38f98a149e5a8b292bed8ddb0ed846b173ebe26", "title": "Rel-grams: A Probabilistic Model of Relations in Text", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W12-3019, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35217367", "name": "Niranjan Balasubramanian"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "14935c3ffb1cafd53a23d84bec66388a77422435", "title": "Named Entity Recognition in Tweets: An Experimental Study", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/D11-1141, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "15173231", "name": "Sam Clark"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "30d226088c4f00b24ded6367757ad88320cc40aa", "title": "An analysis of open information extraction based on semantic role labeling", "openAccessPdf": {"url": "http://turing.cs.washington.edu/papers/janara-kcap2011.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1999676.1999697?email= or https://doi.org/10.1145/1999676.1999697, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "75ae36f8f3462588a498c4159d05793e77c378a3", "title": "Open Information Extraction: The Second Generation", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.5591/978-1-57735-516-8/IJCAI11-012?email= or https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-012, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38087946", "name": "Anthony Fader"}, {"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "2674444", "name": "Mausam"}], "abstract": null}, {"paperId": "7fa2c21b57aea7b66b408c4d09ae160af8caebd8", "title": "Call for a Shake Up in Search !", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "50452701", "name": "M. Broadhead"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "babf91194d1526d4fd2239860867467dc1abc113", "title": "Inference over the web", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2293353", "name": "Stefan Schoenmackers"}], "abstract": null}, {"paperId": "e23020fdab3e46254468f694c159d7d6a3a9fb55", "title": "Search needs a shake-up", "openAccessPdf": {"url": "https://www.nature.com/articles/476025a.pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1038/476025a?email= or https://doi.org/10.1038/476025a, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "376c2b546b64f5afb4620277f555bc85875d33e7", "title": "Commonsense from the Web: Relation Properties", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "380169dfdf019dd77f3316ab14fefab337113652", "title": "Machine Reading at the University of Washington", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W10-0911, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1759772", "name": "Hoifung Poon"}, {"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "1740213", "name": "Pedro M. Domingos"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2566295", "name": "Raphael Hoffmann"}, {"authorId": "3104292", "name": "Chlo\u00e9 Kiddon"}, {"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "145787377", "name": "Xiao Ling"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "2293353", "name": "Stefan Schoenmackers"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "2110920850", "name": "Fei Wu"}, {"authorId": "1799338", "name": "Congle Zhang"}], "abstract": null}, {"paperId": "38daea2f58b6d96a630f77bdfd38645817d6093d", "title": "Adapting Open Information Extraction to Domain-Specific Relations", "openAccessPdf": {"url": "https://aaai.org/ojs/index.php/aimagazine/article/download/2305/2167", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v31i3.2305?email= or https://doi.org/10.1609/aimag.v31i3.2305, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "144166461", "name": "Brendan Roof"}, {"authorId": "2067528098", "name": "Bo Qin"}, {"authorId": "2110941891", "name": "Shi Xu"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "40cf9b8ac93a4ff89516f60a9e21867bb667104d", "title": "A Latent Dirichlet Allocation Method for Selectional Preferences", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/P10-1044, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "79cd699b6e978491a53c560ea4f00d39254a3711", "title": "Evaluating Lemmatic Communication", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1716865", "name": "Katherine Everitt"}, {"authorId": "31065649", "name": "Chris Lim"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145087222", "name": "Jonathan Pool"}, {"authorId": "36845197", "name": "S. Colowick"}, {"authorId": "144295318", "name": "S. Soderland"}], "abstract": null}, {"paperId": "a238781c50932b9c7145ed90d6e8e08e8ed05638", "title": "Panlingual lexical translation via probabilistic inference", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1016/j.artint.2010.04.020?email= or https://doi.org/10.1016/j.artint.2010.04.020, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2674444", "name": "Mausam"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "123340308", "name": "Kobi Reiter"}, {"authorId": "2066794111", "name": "Michael Skinner"}, {"authorId": "144470312", "name": "M. Sammer"}, {"authorId": "1748118", "name": "J. Bilmes"}], "abstract": "\n \n The bare minimum lexical resource required to translate between a pair of languages is a translation dictionary. Unfortunately, dictionaries exist only between a tiny fraction of the 49 million possible language-pairs making machine translation virtually impossible between most of the languages. This paper summarizes the last four years of our research motivated by the vision of panlingual communication. Our research comprises three key steps. First, we compile over 630 freely available dictionaries over the Web and convert this data into a single representation \u2013 the translation graph. Second, we build several inference algorithms that infer translations between word pairs even when no dictionary lists them as translations. Finally, we run our inference procedure offline to construct PANDICTIONARY\u2013 a sense-distinguished, massively multilingual dictionary that has translations in more than 1000 languages. Our experiments assess the quality of this dictionary and find that we have 4 times as many translations at a high precision of 0.9 compared to the English Wiktionary, which is the lexical resource closest to PANDICTIONARY.\n \n"}, {"paperId": "b71c8e582e8e56d839c962b923b0b79bada2a7f8", "title": "Learning First-Order Horn Clauses from Web Text", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/D10-1106, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2293353", "name": "Stefan Schoenmackers"}, {"authorId": "144815446", "name": "Jesse Davis"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "b88c385baf2511b85edb7f58f074452eabc2be71", "title": "Analysis of a probabilistic model of redundancy in unsupervised information extraction", "openAccessPdf": {"url": "https://doi.org/10.1016/j.artint.2010.04.024", "status": "BRONZE", "license": "publisher-specific-oa", "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/j.artint.2010.04.024?email= or https://doi.org/10.1016/j.artint.2010.04.024, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}], "abstract": null}, {"paperId": "c28e3c23ac4671300e133bec4a09ea0e3c4e2973", "title": "Extracting Sequences from the Web", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/P10-2053, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "38087946", "name": "Anthony Fader"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "cf53bda1fbaf6a70da4dd541423caab72267cf47", "title": "Semantic Role Labeling for Open Information Extraction", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W10-0907, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "fc88dbb1459e1a757f808c374cbd61abb2b84db3", "title": "Identifying Functional Relations in Web Text", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/D10-1123, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "18f1b325c218d321f4491b13f66276d8bd56c2c9", "title": "Lemmatic Machine Translation", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/2009.mtsummit-papers.15, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "31065649", "name": "Chris Lim"}, {"authorId": "2067528098", "name": "Bo Qin"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "2e33297639d801c5551df0786e808639891db708", "title": "Compiling a Massive, Multilingual Dictionary via Probabilistic Inference", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.5555/1687878.1687917", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/P09-1030, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2674444", "name": "Mausam"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "38823289", "name": "Michael Skinner"}, {"authorId": "1748118", "name": "J. Bilmes"}], "abstract": "Can we automatically compose a large set of Wiktionaries and translation dictionaries to yield a massive, multilingual dictionary whose coverage is substantially greater than that of any of its constituent dictionaries? \n \nThe composition of multiple translation dictionaries leads to a transitive inference problem: if word A translates to word B which in turn translates to word C, what is the probability that C is a translation of A? The paper introduces a novel algorithm that solves this problem for 10,000,000 words in more than 1,000 languages. The algorithm yields PanDictionary, a novel multilingual dictionary. PanDictionary contains more than four times as many translations than in the largest Wiktionary at precision 0.90 and over 200,000,000 pairwise translations in over 200,000 language pairs at precision 0.8."}, {"paperId": "404564a6165d368d1cf811b83d437288f476513a", "title": "A Rose is a Roos is a Ruusu: Querying Translations for Web Image Search", "openAccessPdf": {"url": "https://doi.org/10.3115/1667583.1667642", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/P09-2049, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "35837717", "name": "Janara Christensen"}, {"authorId": "2674444", "name": "Mausam"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "We query Web Image search engines with words (e.g., spring) but need images that correspond to particular senses of the word (e.g., flexible coil). Querying with polysemous words often yields unsatisfactory results from engines such as Google Images. We build an image search engine, Idiom, which improves the quality of returned images by focusing search on the desired sense. Our algorithm, instead of searching for the original query, searches for multiple, automatically chosen translations of the sense in several languages. Experimental results show that Idiom outperforms Google Images and other competing algorithms returning 22% more relevant images."}, {"paperId": "8e080117f6cc01fe6ea82472e3ea8686ef943e0f", "title": "What Is This, Anyway: Automatic Hypernym Discovery", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "a90d6b15c192c5f5effb543dcc56f2167b72a928", "title": "What is this, anyway", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "ac356e9a230da62eeed5064a44f450ca225d7fe3", "title": "Identifying interesting assertions from the web", "openAccessPdf": {"url": "http://ai.cs.washington.edu/www/media/papers/tmpsvwXJP.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1645953.1646230?email= or https://doi.org/10.1145/1645953.1646230, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145504534", "name": "J. Fogarty"}], "abstract": null}, {"paperId": "cccb6369a2c208abad8864bd72b709016c0d770b", "title": "(1E,4E)-1,5-Bis(2,4-dimethylphenyl)penta-1,4-dien-3-one", "openAccessPdf": {"url": "https://journals.iucr.org/e/issues/2009/09/00/hb5050/hb5050.pdf", "status": "GOLD", "license": "CCBY", "disclaimer": "Notice: Paper or abstract available at https://pmc.ncbi.nlm.nih.gov/articles/PMC2969860, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2095898988", "name": "Research Showcase"}, {"authorId": "102731574", "name": "Cmu"}, {"authorId": "2250519155", "name": "Jaime G. Carbonell"}, {"authorId": "2250835781", "name": "Yolanda Gil"}, {"authorId": "2251705527", "name": "Daniel Borrajo"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2250493083", "name": "Robert Joseph"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "2251707621", "name": "Dan Kuokka"}, {"authorId": "2250433632", "name": "Steve Minton"}, {"authorId": "2085274879", "name": "Henrik Nordin"}, {"authorId": "2256717306", "name": "Alicia Perez"}, {"authorId": "2251709072", "name": "Santiago Rementeria"}, {"authorId": "2054665160", "name": "Hiroshi Tsuji"}, {"authorId": "2251707899", "name": "Manuela M. Veloso"}, {"authorId": "2055496930", "name": "Dan Kahn"}, {"authorId": "2256800338", "name": "Michael Miller"}, {"authorId": "2248318568", "name": "Ellen Riloff"}, {"authorId": "2251707413", "name": "Blythe"}, {"authorId": "2250453309", "name": "M. Blythe"}, {"authorId": "2250954863", "name": "Mitchell"}, {"authorId": "2071091936", "name": "Kulkarni"}, {"authorId": "2250480376", "name": "Simon"}, {"authorId": "2097206470", "name": "Langley"}, {"authorId": "2250868041", "name": "Shen"}], "abstract": "In the title compound, C21H22O, a derivative of the biologically active compound curcumin, the dihedral angle between the aromatic ring planes is 20.57\u2005(11)\u00b0."}, {"paperId": "dcde6a396b36d7b8a6973e6ac19d44ecb182f158", "title": "Filtering Information Extraction via User-Contributed Knowledge", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "144739109", "name": "Thomas Lin"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145504534", "name": "J. Fogarty"}], "abstract": null}, {"paperId": "241193b8edc93b1b3292467cbf661e23c051f8fd", "title": "Look Ma, No Hands: Analyzing the Monotonic Feature Abstraction for Text Classification", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "5608216e0d28b8ea8091913e0399eaef9f94d1a8", "title": "Redundancy in web-scaled information extraction: probabilistic model and experimental results", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145612610", "name": "Doug Downey"}], "abstract": null}, {"paperId": "5dedad671ea566150798ac9c893a9d196ddeee5d", "title": "Targeted IE methods are transforming into open-ended techniques.", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "6c8898cda9a1f13607e24306f6f64f20e0ff2ae7", "title": "The Tradeoffs Between Open and Traditional Relation Extraction", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/P08-1004, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "6fb0fe906c6d90f8111f5026770e1bbf12975241", "title": "It\u2019s a Contradiction \u2013 no, it\u2019s not: A Case Study using Functional Relations", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.5555/1613715.1613718", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D08-1002, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1863425", "name": "Alan Ritter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Contradiction Detection (CD) in text is a difficult NLP task. We investigate CD over functions (e.g., BornIn(Person)=Place), and present a domain-independent algorithm that automatically discovers phrases denoting functions with high precision. Previous work on CD has investigated hand-chosen sentence pairs. In contrast, we automatically harvested from the Web pairs of sentences that appear contradictory, but were surprised to find that most pairs are in fact consistent. For example, \"Mozart was born in Salzburg\" does not contradict \"Mozart was born in Austria\" despite the functional nature of the phrase \"was born in\". We show that background knowledge about meronyms (e.g., Salzburg is in Austria), synonyms, functions, and more is essential for success in the CD task."}, {"paperId": "cf3ba53a5030b8dd6ec65101b6f5a9b8e4d06f80", "title": "Scaling Textual Inference to the Web", "openAccessPdf": {"url": "https://doi.org/10.3115/1613715.1613727", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/D08-1009, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2293353", "name": "Stefan Schoenmackers"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": "Most Web-based Q/A systems work by finding pages that contain an explicit answer to a question. These systems are helpless if the answer has to be inferred from multiple sentences, possibly on different pages. To solve this problem, we introduce the Holmes system, which utilizes textual inference (TI) over tuples extracted from text. \n \nWhereas previous work on TI (e.g., the literature on textual entailment) has been applied to paragraph-sized texts, Holmes utilizes knowledge-based model construction to scale TI to a corpus of 117 million Web pages. Given only a few minutes, Holmes doubles recall for example queries in three disparate domains (geography, business, and nutrition). Importantly, Holmes's runtime is linear in the size of its input corpus due to a surprising property of many textual relations in the Web corpus---they are \"approximately\" functional in a well-defined sense."}, {"paperId": "d2e2e333420e45586117472d14ed1dbafc5db96e", "title": "Machine reading at web scale", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1341531.1341533?email= or https://doi.org/10.1145/1341531.1341533, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "1c528112d29803c64f27d3b4abab70678d5536ac", "title": "Lexical translation with application to image searching on the web", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/2007.mtsummit-papers.24, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "123340308", "name": "Kobi Reiter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "144470312", "name": "M. Sammer"}], "abstract": null}, {"paperId": "4121cf0b1ceca387c5f3a942240e10061478eaca", "title": "Machine reading : Papers from the AAAI Spring Symposium : Technical Report SS-07-06", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "498bb0efad6ec15dd09d941fb309aa18d6df9f5f", "title": "Open Information Extraction from the Web", "openAccessPdf": {"url": "http://turing.cs.washington.edu/papers/ijcai07.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1409360.1409378?email= or https://doi.org/10.1145/1409360.1409378, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "50452701", "name": "M. Broadhead"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Traditionally, Information Extraction (IE) has focused on satisfying precise, narrow, pre-specified requests from small homogeneous corpora (e.g., extract the location and time of seminars from a set of announcements). Shifting to a new domain requires the user to name the target relations and to manually create new extraction rules or hand-tag new training examples. This manual labor scales linearly with the number of target relations. This paper introduces Open IE (OIE), a new extraction paradigm where the system makes a single data-driven pass over its corpus and extracts a large set of relational tuples without requiring any human input. The paper also introduces TEXTRUNNER, a fully implemented, highly scalable OIE system where the tuples are assigned a probability and indexed to support efficient extraction and exploration via user queries. We report on experiments over a 9,000,000 Web page corpus that compare TEXTRUNNER with KNOWITALL, a state-of-the-art Web IE system. TEXTRUNNER achieves an error reduction of 33% on a comparable set of extractions. Furthermore, in the amount of time it takes KNOWITALL to perform extraction for a handful of pre-specified relations, TEXTRUNNER extracts a far broader set of facts reflecting orders of magnitude more relations, discovered on the fly. We report statistics on TEXTRUNNER\u2019s 11,000,000 highest probability tuples, and show that they contain over 1,000,000 concrete facts and over 6,500,000more abstract assertions."}, {"paperId": "6a5cc7480ee8315886445f25e59ddad5585409e9", "title": "Structured Querying of Web Text Data: A Technical Challenge", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "2114485554", "name": "C. R\u00e9"}, {"authorId": "144823759", "name": "Dan Suciu"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "921ecc36a5eae7b8159cf80429804bc574e71f5b", "title": "AAAI 2007 Spring Symposium Series Reports", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v28i3.2058?email= or https://doi.org/10.1609/aimag.v28i3.2058, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1727336", "name": "T. Barkowsky"}, {"authorId": "1755431", "name": "P. Bruza"}, {"authorId": "2068552", "name": "Z. Dodds"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144436424", "name": "G. Ferguson"}, {"authorId": "1774398", "name": "P. Gmytrasiewicz"}, {"authorId": "4506994", "name": "B. Hommel"}, {"authorId": "145585296", "name": "B. Kuipers"}, {"authorId": "2110629317", "name": "Robert C. Miller"}, {"authorId": "40429476", "name": "L. Morgenstern"}, {"authorId": "2053031790", "name": "Simon Parsons"}, {"authorId": "2652839", "name": "Holger Schultheis"}, {"authorId": "1738469", "name": "A. Tapus"}, {"authorId": "1402807089", "name": "N. Yorke-Smith"}], "abstract": null}, {"paperId": "96531057874ad205c2ca3fc097082325c88d2599", "title": "Navigating Extracted Data with Schema Discovery", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "144823759", "name": "Dan Suciu"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "9a1336dfa2f4c2df080990df2eff6e2bb3389238", "title": "Strategies for lifelong knowledge extraction from the web", "openAccessPdf": {"url": "http://turing.cs.washington.edu/papers/kcapfp05-banko.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1298406.1298425?email= or https://doi.org/10.1145/1298406.1298425, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "9bf587f7ec5ce93fb0f9b93d0db6cca7989bb0b0", "title": "Unsupervised Resolution of Objects and Relations on the Web", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/N07-1016, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3321874", "name": "A. Yates"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "ab2ec3373311c7e577b179d7f295dceccdeb66f3", "title": "Machine reading of web text", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1298406.1298407?email= or https://doi.org/10.1145/1298406.1298407, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Over the last five years or so, the KnowItAll project at the University of Washington has been investigating the hypothesis that a substantial fraction of the knowledge necessary for intelligence can be extracted automatically from text, and specifically from text available on the Web. We believe that the time is ripe for the AI community to set its sights on Machine Reading (MR): the autonomous understanding of text. My talk describes progress towards this goal at the University of Washington, and highlights several open questions."}, {"paperId": "ad10607412e196279bf056d13c8b6fa27fd61f26", "title": "TextRunner: Open Information Extraction on the Web", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.5555/1614164.1614177", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/N07-4013, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3321874", "name": "A. Yates"}, {"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "50452701", "name": "M. Broadhead"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}], "abstract": "Traditional information extraction systems have focused on satisfying precise, narrow, pre-specified requests from small, homogeneous corpora. In contrast, the TextRunner system demonstrates a new kind of information extraction, called Open Information Extraction (OIE), in which the system makes a single, data-driven pass over the entire corpus and extracts a large set of relational tuples, without requiring any human input. (Banko et al., 2007) TextRunner is a fully-implemented, highly scalable example of OIE. TextRunner's extractions are indexed, allowing a fast query mechanism."}, {"paperId": "b214871c7780f1e1030da595af8715bd2962d811", "title": "Sparse Information Extraction: Unsupervised Language Models to the Rescue", "openAccessPdf": {"url": "http://turing.cs.washington.edu/papers/399_ddowney.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/P07-1088, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "2293353", "name": "Stefan Schoenmackers"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "bd16feeabf8773dfaf0eaa836a47d2283ebc7c5b", "title": "Invited Talks and Panels", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1690624", "name": "Alan K. Mackworth"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "c777ac37570fc5d728f2aa4dac66333ee7d91dce", "title": "Information extraction from unstructured web text", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "36445704", "name": "Ana-Maria Popescu"}], "abstract": null}, {"paperId": "c8d92c3adf2418ed970f17ed1272d3ca6bf45581", "title": "Information extraction from the web: techniques and applications", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "d54f4215dbdf272820f080b8fc2cbba99bd634e7", "title": "Locating Complex Named Entities in Web Text", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "50452701", "name": "M. Broadhead"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "0af22620dd832549b3610930df55aa3585daa938", "title": "BE: A search engine for NLP research", "openAccessPdf": {"url": "https://doi.org/10.3115/1628297.1628299", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/W06-1702, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Many modern natural language-processing applications utilize search engines to locate large numbers of Web documents or to compute statistics over the Web corpus. Yet Web search engines are designed and optimized for simple human queries---they are not well suited to support such applications. As a result, these applications are forced to issue millions of successive queries resulting in unnecessary search engine load and in slow applications with limited scalability."}, {"paperId": "36a525620757b62c2577e2a21d593c625b3b0265", "title": "Detecting Parser Errors Using Web-based Semantic Filters", "openAccessPdf": {"url": "http://dl.acm.org/ft_gateway.cfm?id=1610080&type=pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/W06-1604, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3321874", "name": "A. Yates"}, {"authorId": "2293353", "name": "Stefan Schoenmackers"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "NLP systems for tasks such as question answering and information extraction typically rely on statistical parsers. But the efficacy of such parsers can be surprisingly low, particularly for sentences drawn from heterogeneous corpora such as the Web. We have observed that incorrect parses often result in wildly implausible semantic interpretations of sentences, which can be detected automatically using semantic information obtained from the Web. \n \nBased on this observation, we introduce Web-based semantic filtering---a novel, domain-independent method for automatically detecting and discarding incorrect parses. We measure the effectiveness of our filtering system, called Woodward, on two test collections. On a set of TREC questions, it reduces error by 67%. On a set of more complex Penn Treebank sentences, the reduction in error rate was 20%."}, {"paperId": "3913e29110d55a08b7fa6f5ddb6d33dbab475b39", "title": "Expanding the Recall of Relation Extraction by Bootstrapping", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/W06-2208, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2559027", "name": "Junji Tomita"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "3a1ff046baec970619121a74fdb8c122bb2cbf9f", "title": "Structured Queries Over Web Text", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144823759", "name": "Dan Suciu"}], "abstract": null}, {"paperId": "501428daffd5d70d1305582ddec7a93dae1f704e", "title": "Self-supervised relation extraction from the Web", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/s10115-007-0110-6?email= or https://doi.org/10.1007/s10115-007-0110-6, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145864794", "name": "Ronen Feldman"}, {"authorId": "47861681", "name": "Binyamin Rosenfeld"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "74a0e4e2dd522528c053efb6aa702a8b784d1c42", "title": "Ambiguity Reduction for Machine Translation: Human-Computer Collaboration", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://aclanthology.org/2006.amta-papers.22, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "144470312", "name": "M. Sammer"}, {"authorId": "123340308", "name": "Kobi Reiter"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1783839", "name": "K. Kirchhoff"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "cdb0efae2bad7e09832950423785c1da3299054e", "title": "Relational Web Search", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f9cbf54dd6b1adc699328b555c4bc03b42ce5851", "title": "Machine Reading", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2339397", "name": "Michele Banko"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}], "abstract": null}, {"paperId": "310cd6a39b0539193561148cd9897b1953fa8b28", "title": "A Probabilistic Model of Redundancy in Information Extraction", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/etzioni/papers/ijcai.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.21236/ada454763?email= or https://doi.org/10.21236/ada454763, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}], "abstract": null}, {"paperId": "37578ce76f4a2103babb43bbd2a7b7e831e1754d", "title": "An Ecological Forecasting Agent", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "48834077", "name": "R. Nemani"}, {"authorId": "2673188", "name": "Wanlin Pang"}, {"authorId": "1681817", "name": "P. Votava"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "421151fa75e40dd86414215abf29d9f2c052a2e1", "title": "Unsupervised named-entity extraction from the Web: An experimental study", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/etzioni/papers/knowitall-journal.pdf", "status": "BRONZE", "license": "publisher-specific-oa", "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/j.artint.2005.03.001?email= or https://doi.org/10.1016/j.artint.2005.03.001, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "3296031", "name": "T. Shaked"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "5a434e7edc86f581b1345f04c640581eb580390e", "title": "A search engine for natural language applications", "openAccessPdf": {"url": "http://www.www2005.org/cdrom/docs/p442.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/1060745.1060811?email= or https://doi.org/10.1145/1060745.1060811, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8a6926202937c81d4b14b3c859c89d4f688cb745", "title": "ACL-05 Feature Engineering for Machine Learning in Natural Language Processing", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1772625", "name": "Eric K. Ringger"}, {"authorId": "1800354", "name": "Kevin Duh"}, {"authorId": "144422314", "name": "Matthew Richardson"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "143753639", "name": "A. McCallum"}, {"authorId": "2023469", "name": "D. Bikel"}, {"authorId": "1794626", "name": "T. Solorio"}, {"authorId": "144272911", "name": "Adriane Boyd"}, {"authorId": "1405796851", "name": "Whitney Gegg-Harrison"}, {"authorId": "1719404", "name": "Alessandro Moschitti"}, {"authorId": "39783117", "name": "Bonaventura Coppola"}, {"authorId": "2726534", "name": "Daniele Pighin"}, {"authorId": "48949093", "name": "R. Basili"}, {"authorId": "2065248807", "name": "Dan Shen"}, {"authorId": "1708708", "name": "G. Kruijff"}, {"authorId": "2073701841", "name": "Dietrich"}, {"authorId": "35220089", "name": "Roberto Liebscher"}, {"authorId": "1682655", "name": "R. Belew"}, {"authorId": "1395813836", "name": "Dilek Z. Hakkani-T\u00fcr"}, {"authorId": "5108268", "name": "Gokhan Tur"}, {"authorId": "2560102", "name": "A. Chotimongkol"}, {"authorId": "3302531", "name": "David Kauchak"}, {"authorId": "35709566", "name": "Francine R. Chen"}, {"authorId": "1770731", "name": "D. Byron"}, {"authorId": "2417334", "name": "Michael Gamon"}, {"authorId": "2266204", "name": "Anthony Aue"}, {"authorId": "2561225", "name": "D. Klakow"}, {"authorId": "3029763", "name": "Tianfang Yao"}, {"authorId": "1781790", "name": "H. Uszkoreit"}], "abstract": null}, {"paperId": "9b0b3ff66c786a7ae534b413e6cbb46ea3bb0be3", "title": "OPINE: Extracting Product Features and Opinions from Reviews", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.3115/1225733.1225750", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/H05-2017, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "2057585328", "name": "Bao Nguyen"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Consumers have to often wade through a large number of on-line reviews in order to make an informed product choice. We introduce OPINE, an unsupervised, high-precision information extraction system which mines product reviews in order to build a model of product features and their evaluation by reviewers."}, {"paperId": "fe8dc921ebe4f85969f4181c50959fa0dc552476", "title": "KnowItNow: Fast, Scalable Information Extraction from the Web", "openAccessPdf": {"url": "https://doi.org/10.3115/1220575.1220646", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/H05-1071, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Numerous NLP applications rely on search-engine queries, both to extract information from and to compute statistics over the Web corpus. But search engines often limit the number of available queries. As a result, query-intensive NLP applications such as Information Extraction (IE) distribute their query load over several days, making IE a slow, offline process.This paper introduces a novel architecture for IE that obviates queries to commercial search engines. The architecture is embodied in a system called KnowItNow that performs high-precision IE in minutes instead of days. We compare KnowItNow experimentally with the previously-published KnowItAll system, and quantify the tradeoff between recall and speed. KnowItNow's extraction rate is two to three orders of magnitude higher than KnowItAll's."}, {"paperId": "ff75055d4e47737702d3b550879d6128cec13233", "title": "Extracting Product Features and Opinions from Reviews", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.3115/1220575.1220618", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/H05-1043, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Consumers are often forced to wade through many on-line reviews in order to make an informed product choice. This paper introduces Opine, an unsupervised information-extraction system which mines reviews in order to build a model of important product features, their evaluation by reviewers, and their relative quality across products.Compared to previous work, Opine achieves 22% higher precision (with only 3% lower recall) on the feature extraction task. Opine's novel use of relaxation labeling for finding the semantic orientation of words in context leads to strong performance on the tasks of finding opinion phrases and their polarity."}, {"paperId": "11271c64e6113386f227af0abc9deaf791ebedf5", "title": "An Agent-Based Interface to Terrestrial Ecological Forecasting", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "48834077", "name": "R. Nemani"}, {"authorId": "2673188", "name": "Wanlin Pang"}, {"authorId": "1681817", "name": "P. Votava"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "3124bf6eaaa233a8a799ed5080f4a9fa1c757674", "title": "Statistical methods for analyzing speedup learning experiments", "openAccessPdf": {"url": "https://link.springer.com/content/pdf/10.1007/BF00993983.pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/BF00993983?email= or https://doi.org/10.1007/BF00993983, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2933110", "name": "Ruth Etzioni"}], "abstract": null}, {"paperId": "400cf0a4a689f65681a4c618471387ea61598283", "title": "Methods for Domain-Independent Information Extraction from the Web: An Experimental Comparison", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "3296031", "name": "T. Shaked"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "49a8ae5eb474e7f6ce3669f9c55efaee1d43cdec", "title": "Modern Natural Language Interfaces to Databases: Composing Statistical Parsing with Semantic Tractability", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.3115/1220355.1220376", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://aclanthology.org/C04-1021, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "2177004", "name": "Alex Armanasu"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2061196271", "name": "David Ko"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": "Natural Language Interfaces to Databases (NLIs) can benefit from the advances in statistical parsing over the last fifteen years or so. However, statistical parsers require training on a massive, labeled corpus, and manually creating such a corpus for each database is prohibitively expensive. To address this quandary, this paper reports on the PRECISE NLI, which uses a statistical parser as a \"plug in\". The paper shows how a strong semantic model coupled with \"light re-training\" enables PRECISE to overcome parser errors, and correctly map from parsed questions to the corresponding SQL queries. We discuss the issues in using statistical parsers to build database-independent NLIs, and report on experimental results with the benchmark ATIS data set where PRECISE achieves 94% accuracy."}, {"paperId": "9ac20c401a1d320ef4a15ed1cfb33317c64a704c", "title": "Meaning for the masses: theory and applications for semantic web and semantic email systems", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}], "abstract": null}, {"paperId": "9ef07373873cc0f0b940512dcdde4e7b54b0cfb0", "title": "Web-scale information extraction in knowitall: (preliminary results)", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/weld/papers/www-paper.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/988672.988687?email= or https://doi.org/10.1145/988672.988687, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1725561", "name": "Michael J. Cafarella"}, {"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "3447955", "name": "Stanley Kok"}, {"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "3296031", "name": "T. Shaked"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "b064dedeffbe16e61d5f797db651bbfd538c4e72", "title": "Semantic email", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/988672.988706?email= or https://doi.org/10.1145/988672.988706, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "36105267", "name": "H. Levy"}], "abstract": null}, {"paperId": "b074a937a6f3f8c1d9aab9d695fa4ab3c213875b", "title": "PRECISE on ATIS: Semantic Tractability and Experimental Results", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "2177004", "name": "Alex Armanasu"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2061196271", "name": "David Ko"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "c2eb9e613466590a0460b3a30fed8e1283dc18b0", "title": "The Specification of Agent Behavior by Ordinary People: A Case Study", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/978-3-540-30475-3_14?email= or https://doi.org/10.1007/978-3-540-30475-3_14, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}], "abstract": null}, {"paperId": "c5317bd39b8d11a5b23b050d0e6722e6304462c4", "title": "Semantic email: theory and applications", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/j.websem.2004.09.001?email= or https://doi.org/10.1016/j.websem.2004.09.001, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}], "abstract": null}, {"paperId": "cc48c9c458124ed85d02dd676cd8503fab2a8e07", "title": "The use of web-based statistics to validate, information extraction", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3296031", "name": "T. Shaked"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "d1359f4f778e29ff836d02c966d9f8c74a5395ed", "title": "Class Extraction from the World Wide Web", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "3321874", "name": "A. Yates"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "feb37c17b4b5e8b304545f2f40a45c335302b21b", "title": "Specifying Semantic Email Processes", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}], "abstract": null}, {"paperId": "0df4b1ce53c4b874720b330b60eb175265341569", "title": "To Buy or Not to Buy: Mining Airline Fare Data to Minimize Ticket Purchase Price", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "2479932", "name": "Rattapoom Tuchinda"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "26dfb487506efcb9100053bcbd380ce160762f18", "title": "A reliable natural language interface to household appliances", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/604045.604075?email= or https://doi.org/10.1145/604045.604075, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3321874", "name": "A. Yates"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "477b87cf0fc5d830338a3998a2422bd369a81bda", "title": "Foundations of Assisted Cognition Systems", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1690271", "name": "Henry A. Kautz"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145197953", "name": "D. Fox"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "48462607", "name": "L. Shastri"}], "abstract": null}, {"paperId": "80b3c09d900c57218887f0bc1e990c5da649e8fd", "title": "Learning knowledge bases for information extraction from multiple text based Web sites", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1109/IAT.2003.1241057?email= or https://doi.org/10.1109/IAT.2003.1241057, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "82c23c75c2216fc420ce2d66b846e243f0f6e1f3", "title": "Evolving the Semantic Web with Mangrove", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1700451", "name": "S. Gribble"}, {"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2945977", "name": "William Pentney"}, {"authorId": "144130626", "name": "D. Verma"}, {"authorId": "1893832", "name": "Stani Vlasseva"}], "abstract": null}, {"paperId": "8d43a96e12a07b53014997f050005e09a62b7cef", "title": "Crossing the Structure Chasm", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3030274", "name": "A. Doan"}, {"authorId": "1804315", "name": "Z. Ives"}, {"authorId": "2224716", "name": "Jayant Madhavan"}, {"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "3182988", "name": "I. Tatarinov"}], "abstract": null}, {"paperId": "985b64bf03e3655112bed87f6aee08fdf6191998", "title": "Automatically personalizing user interfaces", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "20519220", "name": "Corin R. Anderson"}, {"authorId": "1740213", "name": "Pedro M. Domingos"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770992", "name": "Krzysztof Z Gajos"}, {"authorId": "143907654", "name": "T. Lau"}, {"authorId": "3162853", "name": "S. Wolfman"}], "abstract": null}, {"paperId": "b43e0bb7e5393502fc599ecb22aa055839a03d4a", "title": "To buy or not to buy: mining airfare data to minimize ticket purchase price", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/956750.956767?email= or https://doi.org/10.1145/956750.956767, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2479932", "name": "Rattapoom Tuchinda"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "3321874", "name": "A. Yates"}], "abstract": null}, {"paperId": "b50f78c9534182a09c060580811274928702b38d", "title": "Towards a theory of natural language interfaces to databases", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/604045.604070?email= or https://doi.org/10.1145/604045.604070, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "36445704", "name": "Ana-Maria Popescu"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1690271", "name": "Henry A. Kautz"}], "abstract": "The need for Natural Language Interfaces to databases (NLIs) has become increasingly acute as more and more people access information through their web browsers, PDAs, and cell phones. Yet NLIs are only usable if they map natural language questions to SQL queries correctly. As Schneiderman and Norman have argued, people are unwilling to trade reliable and predictable user interfaces for intelligent but unreliable ones. In this paper, we introduce a theoretical framework for reliable NLIs, which is the foundation for the fully implemented Precise NLI. We prove that, for a broad class of semantically tractable natural language questions, Precise is guaranteed to map each question to the corresponding SQL query. We report on experiments testing Precise on several hundred questions drawn from user studies over three benchmark databases. We find that over 80% of the questions are semantically tractable questions, which Precise answers correctly. Precise automatically recognizes the 20% of questions that it cannot handle, and requests a paraphrase. Finally, we show that Precise compares favorably with Mooney's learning NLI and with Microsoft's English Query product"}, {"paperId": "b9780458992e436e1ba4307e6de8b7bc3483809f", "title": "Mangrove: Enticing Ordinary People onto the Semantic Web via Instant Gratification", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/978-3-540-39718-2_48?email= or https://doi.org/10.1007/978-3-540-39718-2_48, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2956720", "name": "Luke K. McDowell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1700451", "name": "S. Gribble"}, {"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2945977", "name": "William Pentney"}, {"authorId": "144130626", "name": "D. Verma"}, {"authorId": "1893832", "name": "Stani Vlasseva"}], "abstract": null}, {"paperId": "b98f2bcfefdcbeb2942ef4be8d545d936a7f01bd", "title": "Session details: Data mining", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/3245010?email= or https://doi.org/10.1145/3245010, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "dba4c463f8cb75ad03ce9e9939802f6fe4661aea", "title": "Semantic Email: Adding Lightweight Data Manipulation Capabilities to the Email Habitat", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2956720", "name": "Luke K. McDowell"}], "abstract": null}, {"paperId": "e35cda30869d6eb0cc384e5876be455e97dd1163", "title": "Towards a Theory of Question-Answering Interfaces to Databases", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "41192561", "name": "A. Popescu"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1690271", "name": "Henry A. Kautz"}], "abstract": null}, {"paperId": "4ab87b0be1cd97842b71b570eba723cf7b50681b", "title": "Learning Text Patterns for Web Information Extraction and Assessment", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "145612610", "name": "Doug Downey"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "598c3ed32947b914bd4bbfc0761bd554a9abfd3f", "title": "A Grammar Inference Algorithm for the World Wide Web", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2471487", "name": "Terrance Goan"}, {"authorId": "152540692", "name": "S. Henke"}, {"authorId": "31805569", "name": "Nels E. Benson"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "81bc7587b9b544ad49285b51a6fd6c84c5fb6b60", "title": "An Evolutionary Approach to the Semantic Web", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1700451", "name": "S. Gribble"}, {"authorId": "1770962", "name": "A. Halevy"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2956720", "name": "Luke K. McDowell"}], "abstract": null}, {"paperId": "a9af6a700a7586a9f0f86f6c68c8c8835908c93f", "title": "Assisted cognition: Computer aids for people with Alzheimer", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.4017/GT.2002.02.01.016.00?email= or https://doi.org/10.4017/GT.2002.02.01.016.00, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1690271", "name": "Henry A. Kautz"}, {"authorId": "1735801", "name": "G. Borriello"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145197953", "name": "D. Fox"}], "abstract": null}, {"paperId": "af4db041c61e5bd7408a94dabe0d684d6bd2bfcb", "title": "Intelligent Ubiquitous Computing to Support Alzheimer \u2019 s Patients : Enabling the Cognitively Disabled", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "143712289", "name": "Donald J. Patterson"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145197953", "name": "D. Fox"}, {"authorId": "1690271", "name": "Henry A. Kautz"}], "abstract": null}, {"paperId": "b930d6d071f6a02118bc068ecf4137e39670422f", "title": "An Overview of the Assisted Cognition Project", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1690271", "name": "Henry A. Kautz"}, {"authorId": "145197953", "name": "D. Fox"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1735801", "name": "G. Borriello"}, {"authorId": "3251663", "name": "L. Arnstein"}], "abstract": null}, {"paperId": "016e9cc85c658c6a69710b4c617609ad2a5d3a74", "title": "Scaling question answering to the Web", "openAccessPdf": {"url": "http://www.www10.org/cdrom/papers/pdf/p120.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/371920.371973?email= or https://doi.org/10.1145/371920.371973, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1983124", "name": "Cody C. T. Kwok"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": "The wealth of information on the web makes it an attractive resource for seeking quick answers to simple, factual questions such as "e;who was the first American in space?"e; or "e;what is the second tallest mountain in the world?"e; Yet today's most advanced web search services (e.g., Google and AskJeeves) make it surprisingly tedious to locate answers to such questions. In this paper, we extend question-answering techniques, first studied in the information retrieval literature, to the web and experimentally evaluate their performance.First we introduce Mulder, which we believe to be the first general-purpose, fully-automated question-answering system available on the web. Second, we describe Mulder's architecture, which relies on multiple search-engine queries, natural-language parsing, and a novel voting procedure to yield reliable answers coupled with high recall. Finally, we compare Mulder's performance to that of Google and AskJeeves on questions drawn from the TREC-8 question answering track. We find that Mulder's recall is more than a factor of three higher than that of AskJeeves. In addition, we find that Google requires 6.6 times as much user effort to achieve the same level of recall as Mulder."}, {"paperId": "204001cded2086939e1a54e4fb58dfadae56d8f6", "title": "High tech or high touch (panel session): automation and human mediation in libraries", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/379437.379725?email= or https://doi.org/10.1145/379437.379725, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2052679642", "name": "D. Levy"}, {"authorId": "1782424", "name": "William Y. Arms"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "31934481", "name": "D. Nester"}, {"authorId": "67027722", "name": "B. Tillett"}], "abstract": null}, {"paperId": "e0c05d628604a23f8fc8ff195a55f50683344d9a", "title": "Adaptive Web Site : Cluster Mining and Conceptual Clustering for Index Page Synthesis", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f2fb8d919a9e54d29648548ad3b7dd0c21343bef", "title": "High tech or high touch: automation and human mediation in libraries (panel session)", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/379437.379725?email= or https://doi.org/10.1145/379437.379725, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2052679642", "name": "D. Levy"}, {"authorId": "1782424", "name": "William Y. Arms"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "31934481", "name": "D. Nester"}, {"authorId": "67027722", "name": "B. Tillett"}], "abstract": null}, {"paperId": "1749b924645fb6e5ec66fbfdd82fbc66d86054c3", "title": "Patricia Riddle* Boeing", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "29838575", "name": "P. Riddle"}], "abstract": null}, {"paperId": "1e89dba9d756a606b3f86e407053036e944216bb", "title": "On the Instability of Web Sear", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "52a7fda321519de58e1c63ee4d99c71cc14ded72", "title": "Adaptive Web sites", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.1145/345124.345171", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/345124.345171?email= or https://doi.org/10.1145/345124.345171, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "D esigning a complex Web site so that it readily yields its information is a difficult task. The designer must anticipate the users' needs and structure the site accordingly. Yet users may have vastly differing views of the site's information, their needs may change over time, and their usage patterns may violate the designer's initial expectations. As a result, Web sites are all too often fossils cast in HTML, while user navigation is idiosyncratic and evolving. Understanding user needs requires understanding how users view the data available and how they actually use the site. For a complex site this can be difficult since user tests are expensive and time-consuming, and the site's server logs contain massive amounts of data. We propose a Web management assistant: a system that can process massive amounts of data about site usage Examining the potential use of automated adaptation to improve Web sites for visitors."}, {"paperId": "7594145357db0e99c45109e8d5620cee01c21f7c", "title": ".1 Motivation", "openAccessPdf": {"url": "https://www.peterlang.com/downloadpdf/9783653980622/11_Chapter01.html.pdf", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.3726/978-3-653-02175-2/7?email= or https://doi.org/10.3726/978-3-653-02175-2/7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "7765c769cf5c032e23eae17c3dc81ce348484482", "title": "Moving U p the Information Food Chairl : Deploying Softbots on the World Wide \" \\ i \\ Teb", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "826cc30666bccc0eb2617ba360edeafe17e40f09", "title": "Homogeneous Rules", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2320198165", "name": "E. Segal"}], "abstract": null}, {"paperId": "8fdf45c231e816e303f5962a16ec270207edf1a5", "title": "Optimal Information Gathering on the Internet with Time and Cost Constraints", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1137/S0097539797314465?email= or https://doi.org/10.1137/S0097539797314465, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "143872539", "name": "T. Jiang"}, {"authorId": "1734627", "name": "Omid Madani"}], "abstract": null}, {"paperId": "a90a5e0fb1b2d80ca4856d60b5026402c97c2dcf", "title": "On the Instability of Web Search Engines", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.5555/2835865.2835889?email= or https://doi.org/10.5555/2835865.2835889, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f6b160f9ea596466769fd4f05de0c73a29c31f32", "title": "Query routing for Web search engines: architecture and experiments", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/etzioni/papers/www9-final.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/S1389-1286(00)00059-1?email= or https://doi.org/10.1016/S1389-1286(00)00059-1, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "46889592", "name": "A. Sugiura"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "6658d13ae5ed3b33c450d335332677ecd4d671a5", "title": "Proceedings of the third annual conference on Autonomous Agents", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1735267", "name": "J. M\u00fcller"}, {"authorId": "2269809402", "name": "Jeffrey M. Bradshaw"}], "abstract": null}, {"paperId": "8634fc24b196f1cafb85aea1ad2a272690cbb829", "title": "Towards adaptive Web sites: Conceptual framework and case study", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/etzioni/papers/perkowitz_www8.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1016/S0004-3702(99)00098-3?email= or https://doi.org/10.1016/S0004-3702(99)00098-3, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Abstract The creation of a complex Web site is a thorny problem in user interface design. In this paper we explore the notion of adaptive Web sites : sites that semi-automatically improve their organization and presentation by learning from visitor access patterns. It is easy to imagine and implement Web sites that offer shortcuts to popular pages. Are more sophisticated adaptive Web sites feasible? What degree of automation can we achieve? To address the questions above, we describe the design space of adaptive Web sites and consider a case study: the problem of synthesizing new index pages that facilitate navigation of a Web site. We present the PageGather algorithm, which automatically identifies candidate link sets to include in index pages based on user access logs. We demonstrate experimentally that PageGather outperforms the Apriori data mining algorithm on this task. In addition, we compare PageGather's link sets to pre-existing, human-authored index pages."}, {"paperId": "87dc7b2aac1a96ccea0bd1688373a59aa6dc434d", "title": "Adaptive Web Sites: Conceptual Cluster Mining", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "a2ecbf91c96b378b33100bfe9049b2462cfd817f", "title": "Agents vs. direct manipulation: what's best to disentangle the Web?", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2107797948", "name": "J. A. S\u00e1nchez"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1690271", "name": "Henry A. Kautz"}, {"authorId": "145507148", "name": "H. Lieberman"}, {"authorId": "1740403", "name": "B. Shneiderman"}], "abstract": null}, {"paperId": "aa91d13317efe5951d46ef8887832a7f162c978d", "title": "Face-to-Face and Computer-Mediated Communities, A Comparative Analysis", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1080/019722499128402?email= or https://doi.org/10.1080/019722499128402, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "In this article we combine the perspectives of sociology and computer science to compare face-to-face (f2f) and computer-mediated communications (CMC) from the viewpoint of their respective abilities to form and sustain communities. We also identify a third type of community-a hybrid-that is based on a combination of faceto-face (f2f) and CMC, or off- and online communications. The article thus in effect addresses an oft-asked question: Can virtual communities be \"real\", have the same basic qualities as f2f communities? The article is exploratory, because much of the necessary evidence has not yet been generated, and the relevant technologies are rapidly changing."}, {"paperId": "c7288d6b123dbf547df177b8e4014942b5419e06", "title": "Privacy interfaces for information management", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.1145/317665.317680", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/317665.317680?email= or https://doi.org/10.1145/317665.317680, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "143907654", "name": "T. Lau"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "d5a2b055c8cded61a1112de0abd06586bd604bd6", "title": "Grouper: A Dynamic Clustering Interface to Web Search Results", "openAccessPdf": {"url": "http://www.cs.washington.edu/homes/etzioni/papers/www8.pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/S1389-1286(99)00054-7?email= or https://doi.org/10.1016/S1389-1286(99)00054-7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e10fb8823476d2728a1c51302bdf0fccd12e0920", "title": "Proceedings of the Third International Conference on Autonomous Agents: Seattle, WA, USA, May 1-5, 1999", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1735267", "name": "J. M\u00fcller"}, {"authorId": "2694626", "name": "J. Bradshaw"}], "abstract": null}, {"paperId": "e59f829e4f1384a039da88c6f1c8fc796ab21929", "title": "3 Suffix Tree Clustering", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e8af0a6c90c2bdf5fffb674a41767b926396a555", "title": "Clustering web documents: a phrase-based method for grouping search engine results", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e92deec1c94c7ffa779490c5a5518886e85951f4", "title": "Towards comprehensive web search", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f7f6a296a0d88007e06a1eae8ba9d046e208f96d", "title": "October 19ber 14 42, No. 10COMMUNICAT0 T OF T HE ACM", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "143907654", "name": "T. Lau"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "14e33b6ae8431608d387474f61c72e093915a55a", "title": "Predicting Event Sequences: Data Mining for Prefetching Web-pages", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145864794", "name": "Ronen Feldman"}, {"authorId": "2293438", "name": "T. Shmiel"}, {"authorId": "2090792", "name": "Y. Aumann"}], "abstract": null}, {"paperId": "3314c3f62d9ccef221f3d26972aa65b1cda30cc1", "title": "A Redundant Covering Algorithm Applied to Text Classification", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2283007734", "name": "D. Hsu"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "144295318", "name": "S. Soderland"}], "abstract": null}, {"paperId": "58ba55263d6e85018517c9545ce4b2d8c216dad7", "title": "Web document clustering: a feasibility demonstration", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/290941.290956?email= or https://doi.org/10.1145/290941.290956, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Users of Web search engines are often forced to sift through the long ordered list of document \"snippets\" returned by the engines. The IR community has explored document clustering as an alternative method of organizing retrieval results, but clustering has yet to be deployed on the major search engines. The paper articulates the unique requirements of Web document clustering and reports on the first evaluation of clustering methods in this domain. A key requirement is that the methods create their clusters based on the short snippets returned by Web search engines. Surprisingly, we find that clusters based on snippets are almost as good as clusters created using the full text of Web documents. To satisfy the stringent requirements of the Web domain, we introduce an incremental, linear time (in the document collection size) algorithm called Suffix Tree Clustering (STC). which creates clusters based on phrases shared between documents. We show that STC is faster than standard clustering methods in this domain, and argue that Web document clustering via STC is both feasible and potentially beneficial."}, {"paperId": "97013d7af208b6320abde16954a190a02828051d", "title": "Adaptive Web Sites: Automatically Synthesizing Web Pages", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "c79da581202031bca7a3409615daf89f8e406d1b", "title": "Web document clustering", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e7ff9fade22be046f004508e6faedaaaf12e4da5", "title": "Scalable and adaptive goal recognition", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3012739", "name": "N. Lesh"}], "abstract": null}, {"paperId": "32c4fd87ccccf21880ff70f46875788942a66311", "title": "Dynamic Reference Sifting: A Case Study in the Homepage Domain", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/S0169-7552(97)00048-2?email= or https://doi.org/10.1016/S0169-7552(97)00048-2, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2105119697", "name": "Jonathan Shakes"}, {"authorId": "47085377", "name": "Marc Langheinrich"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "5c1a062cec3e35eb130571dba47f18b294bfc8d2", "title": "Fast and Intuitive Clustering of Web Documents", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2360279", "name": "Oren Zamir"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1734627", "name": "Omid Madani"}, {"authorId": "47546648", "name": "R. Karp"}], "abstract": null}, {"paperId": "69eaf2e1fc27b7ae612f979645f2683ebf8487a9", "title": "Experiments with Collaborative Index Enhancement", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "6eba9d9bd73349de9cd01e05f6b8e2ca0bf63a85", "title": "An Introduction to this Special Issue of AI Magazine", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/AIMAG.V18I2.1288?email= or https://doi.org/10.1609/AIMAG.V18I2.1288, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "77e2e742d53ef382df9f896abadf291646eed3cc", "title": "The MetaCrawler architecture for resource aggregation on the Web", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1109/64.577468?email= or https://doi.org/10.1109/64.577468, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "7b3b14828a71c3bd4e56fda87a8c89a72d358c4e", "title": "A scalable comparison-shopping agent for the World-Wide Web", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/267658.267666?email= or https://doi.org/10.1145/267658.267666, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2913159", "name": "Robert B. Doorenbos"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "7ffa695066b9a5d7438cf788fc0faba554ed6aed", "title": "Sound and Efficient Closed-World Reasoning for Planning", "openAccessPdf": {"url": "https://doi.org/10.1016/s0004-3702(96)00026-4", "status": "BRONZE", "license": "publisher-specific-oa", "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/S0004-3702(96)00026-4?email= or https://doi.org/10.1016/S0004-3702(96)00026-4, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "a4b465f0d837cf9bbe64f0c1e70fa164dea9deed", "title": "Learning to Understand Information on the Internet: An Example-Based Approach", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1023/A:1008672508721?email= or https://doi.org/10.1023/A:1008672508721, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "2913159", "name": "Robert B. Doorenbos"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "a913830b3c2177fdf2370f861f4812051a3a2a2b", "title": "Communities: Virtual vs. Real", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1126/SCIENCE.277.5324.295?email= or https://doi.org/10.1126/SCIENCE.277.5324.295, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f0418a3fc360199ec2b52fcfa979180d3bd3e6f4", "title": "Adaptive Web Sites: an AI Challenge", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "3202a19af7c85ea0948a6b1b7b1c60ed199c94ba", "title": "Scaling Up Goal Recognition", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "5f9b342307b1149615a49486ff7d2abf783314ff", "title": "The World-Wide Web: quagmire or gold mine?", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.1145/240455.240473", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/240455.240473?email= or https://doi.org/10.1145/240455.240473, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8a9ac681cfd1f0e0ffa76902d333fc822614e174", "title": "Planning with Execution and Incomplete Information", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "cbd0dfef8bd94ca8aadccfa404d93b1b621ff0f1", "title": "Efficient Information Gathering on the Internet* (extended abstract)", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "143872539", "name": "T. Jiang"}, {"authorId": "47546648", "name": "R. Karp"}, {"authorId": "1734627", "name": "Omid Madani"}, {"authorId": "1747243", "name": "Orli Waarts"}], "abstract": null}, {"paperId": "cfdfc00d1bfd4fb635276f18d81bc6b79b7a0785", "title": "Moving Up the Information Food Chain: Deploying Softbots on the World Wide Web", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v18i2.1289?email= or https://doi.org/10.1609/aimag.v18i2.1289, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "d8ab36551e25f158a1f2b9d2596929d1cd3d643a", "title": "Efficient information gathering on the Internet", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1109/SFCS.1996.548482?email= or https://doi.org/10.1109/SFCS.1996.548482, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "143872550", "name": "Tao Jiang"}, {"authorId": "47546648", "name": "R. Karp"}, {"authorId": "1734627", "name": "Omid Madani"}, {"authorId": "1747243", "name": "Orli Waarts"}], "abstract": "The Internet offers unprecedented access to information. At present most of this information is free, but information providers ore likely to start charging for their services in the near future. With that in mind this paper introduces the following information access problem: given a collection of n information sources, each of which has a known time delay, dollar cost and probability of providing the needed information, find an optimal schedule for querying the information sources. We study several variants of the problem which differ in the definition of an optimal schedule. We first consider a cost model in which the problem is to minimize the expected total cost (monetary and time) of the schedule, subject to the requirement that the schedule may terminate only when the query has been answered or all sources have been queried unsuccessfully. We develop an approximation algorithm for this problem and for an extension of the problem in which more than a single item of information is being sought. We then develop approximation algorithms for a reward model in which a constant reward is earned if the information is successfully provided, and we seek the schedule with the maximum expected difference between the reward and a measure of cost. The monetary and time costs may either appear in the cost measure or be constrained not to exceed a fixed upper bound; these options give rise to four different variants of the reward model."}, {"paperId": "00a8c7ee6fa61df374d1cf7ec0e0753004542a3d", "title": "Insights from Machine Learning for Plan Recognition", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "05c92c1593707c60d96275645ee15e6adfc79a71", "title": "Multi-Service Search and Comparison Using the MetaCrawler", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "29f7471ee566dc8e7a95d722318e45810c255029", "title": "A Sound and Fast Goal Recognizer", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "79eb8706ed0496da4659b16ffa83dd18198f1dd3", "title": "Intelligent Agents on the Internet: Fact, Fiction, and Forecast", "openAccessPdf": {"url": "https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.6.7045&rep=rep1&type=pdf", "status": "GREEN", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1109/64.403956?email= or https://doi.org/10.1109/64.403956, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "7dabaac2a302bf2c99cd21341802fbe885398408", "title": "Category Translation: Learning to Understand Information on the Internet", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "9cd864c49f2b328842d4545ab7e6f554c312c016", "title": "Multi-Engine Search and Comparison Using the MetaCrawler", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.1145/3592626.3592641", "status": "BRONZE", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1145/3592626.3592641?email= or https://doi.org/10.1145/3592626.3592641, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "3236427", "name": "E. Selberg"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": "Standard Web search services, though useful, are far from ideal. There are over a dozen different search services currently in existence, each with a unique interface and a database covering a different portion of the Web. As a result, users are forced to repeatedly try and retry their queries across different services. Furthermore, the services return many responses that are irrelevant, outdated, or unavailable, forcing the user to manually sift through the responses searching for useful information. This paper presents the MetaCrawler, a fielded Web service that represents the next level up in the information \"food chain.\" The MetaCrawler provides a single, central interface for Web document searching. Upon receiving a query, the MetaCrawler posts the query to multiple search services in parallel, collates the returned references, and loads those references to verify their existence and to ensure that they contain relevant information. The MetaCrawler is sufficiently lightweight to reside on a user's machine, which facilitates customization, privacy, sophisticated filtering of references, and more. The MetaCrawler also serves as a tool for comparison of diverse search services. Using the MetaCrawler's data, we present a \"Consumer Reports\" evaluation of six Web search services: Galaxy [5], InfoSeek [1], Lycos [15], Open Text [20], WebCrawler [22], and Yahoo [9]. In addition, we also report on the most commonly submitted queries to the MetaCrawler."}, {"paperId": "e712c496e2463b0c160356ea2bd9bf35521ebc72", "title": "The Softbot Approach to OS Interfaces", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1109/52.391830?email= or https://doi.org/10.1109/52.391830, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1780447", "name": "C. A. Thekkath"}], "abstract": null}, {"paperId": "050584e3b74d1d7f5396d379510ca5204f02bfc1", "title": "A softbot-based interface to the Internet", "openAccessPdf": {"url": "https://dl.acm.org/doi/pdf/10.1145/176789.176797", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/176789.176797?email= or https://doi.org/10.1145/176789.176797, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "07dca271ebff4a9126ad1f8e4e96465a4cb746ab", "title": "Database Learning for Software Agents", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "3017541", "name": "Mike Perkowitz"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "0a29e4f2364f69f72bc3763c9a5f8f324d9cfc4c", "title": "Statistical Methods for Analyzing Speedup Learning Experiments", "openAccessPdf": {"url": "https://link.springer.com/content/pdf/10.1023/A:1022617931401.pdf", "status": "BRONZE", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1023/A:1022617931401?email= or https://doi.org/10.1023/A:1022617931401, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "2933110", "name": "Ruth Etzioni"}], "abstract": null}, {"paperId": "2326e2fcd243e31cfe20ab1b255074990ac6218a", "title": "Omnipotence Without Omniscience: Efficient Sensor Management for Planning", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "40942452eda7af86e827b4c750918ef7f1ed843e", "title": "Xii: Planning with Universal Quantification and Incomplete Information", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "4526a83672b221b75123d75ce86bf01e097e7fe2", "title": "Learning Decision Lists Using Homogeneous Rules", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "4e1a8d5159eb47b959ccedde98eee84a1f3b8275", "title": "The First Law of Robotics (A Call to Arms)", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1007/978-3-642-04879-1_7?email= or https://doi.org/10.1007/978-3-642-04879-1_7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "5ff3d9f18b60dfae657186a56822540d87f81e91", "title": "Omnipotence without Omniscience: Sensor Management in Planning", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "8773608109dcd7df7f951bdb09b6ba40d9545075", "title": "Planning with Universal Quanti cation and Incomplete Information", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "8ad8d2d8a1365a4217b7593a9e5baac65b271aac", "title": "Learning About Software Errors Via Systematic Experimentation", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2471487", "name": "Terrance Goan"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "9c9efdcb107a8e5d3308ad38c6967cc52004293f", "title": "Representation design and brute-force induction in a Boeing manufacturing domain", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1080/08839519408945435?email= or https://doi.org/10.1080/08839519408945435, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "29838575", "name": "P. Riddle"}, {"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "bb4a4d29ab4599157502c1960425196a39cb6ad1", "title": "Tractable Closed World Reasoning with Updates", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/B978-1-4832-1452-8.50113-5?email= or https://doi.org/10.1016/B978-1-4832-1452-8.50113-5, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "c22ac43484442ad1a300a2f4fe120bc6669b29cb", "title": "Omnipotence Without Omniscience: Efficient Sensor Management for Software Agents", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1888618", "name": "Keith Golden"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1780531", "name": "Daniel S. Weld"}], "abstract": null}, {"paperId": "d6ad861315750e470fb9224d3b722f64525d52b6", "title": "Learning Decision Lists Using Homogeneous", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "0621b4fbe20b2a04fd6d5e684fe5808d1304fd6d", "title": "Planning with Incomplete Information in the UNIX Domain", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3012739", "name": "N. Lesh"}], "abstract": null}, {"paperId": "6ddc20248f15e7326d1b48f455152eee98d993d6", "title": "OS Agents: Using AI Techniques in the Operating System Environment", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "36105267", "name": "H. Levy"}, {"authorId": "2229222", "name": "R. Segal"}, {"authorId": "1780447", "name": "C. A. Thekkath"}], "abstract": null}, {"paperId": "a5af977ce4242cc0c4e249d7dac0c6c2ef58bdd4", "title": "Intelligence without Robots: A Reply to Brooks", "openAccessPdf": {"url": "", "status": null, "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1609/aimag.v14i4.1065?email= or https://doi.org/10.1609/aimag.v14i4.1065, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "c69ea4635a7fbf2af9f5025d26531d64af0a98d5", "title": "Acquiring Search-Control Knowledge via Static Analysis", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/0004-3702(93)90080-U?email= or https://doi.org/10.1016/0004-3702(93)90080-U, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "f3f2e9ed667005015746a59451ddb910191edc5d", "title": "A Structural Theory of Explanation-Based Learning", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/0004-3702(93)90035-A?email= or https://doi.org/10.1016/0004-3702(93)90035-A, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "081e78ef3c81811b763457eaa8138dcfbc417b82", "title": "DYNAMIC: A New Role for Training Problems in EBL", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/b978-1-55860-247-2.50052-8?email= or https://doi.org/10.1016/b978-1-55860-247-2.50052-8, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "2110825357", "name": "M. A. P\u00e9rez"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "1b2186798dc4150d54d0953622bbae5dd9742eac", "title": "Why EBL Produces Overly-Specific Knowledge: A Critique of the PRODIGY Approaches", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/b978-1-55860-247-2.50023-1?email= or https://doi.org/10.1016/b978-1-55860-247-2.50023-1, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145293454", "name": "Steven Minton"}], "abstract": null}, {"paperId": "4860f28be5577e658e39bfc78cf50b508d80420f", "title": "Process Improvement through Automated Feedback ( Preliminary Report )", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "29838575", "name": "P. Riddle"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145867780", "name": "Carl Pearson"}, {"authorId": "2229222", "name": "R. Segal"}], "abstract": null}, {"paperId": "59bf142f94ee5193481fde751107a54842cbdaef", "title": "PRODIGY4.0: The Manual and Tutorial", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.21236/ada253970?email= or https://doi.org/10.21236/ada253970, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "143731071", "name": "J. Blythe"}, {"authorId": "143712374", "name": "J. Carbonell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145526918", "name": "Y. Gil"}, {"authorId": "143676491", "name": "R. Joseph"}, {"authorId": "2055496930", "name": "Dan Kahn"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "26602711", "name": "Steven N. Minton"}, {"authorId": "2110390815", "name": "Alicia P\u00e9rez"}, {"authorId": "10216882", "name": "S. Reilly"}, {"authorId": "1956361", "name": "M. Veloso"}, {"authorId": "2108239090", "name": "Xuemei Wang"}], "abstract": "PRODIGY is a general-purpose problem-solving architecture that serves as a basis for research in planning, machine learning, apprentice-type knowledge-refinement interfaces, and expert systems. This document is a manual for the latest version of the PRODIGY system, PRODIGY4.0, and includes descriptions of the PRODIGY representation language, control structure, user interface, abstraction module, and other features. The tutorial style is meant to provide the reader with the ability to run PRODIGY and make use of all the basic features, as well as gradually learning the more esoteric aspects of PRODIGY4.0."}, {"paperId": "5b61dacb90397f176ac8c035a701d06dde975376", "title": "An Approach to Planning with Incomplete Information (extended Abstract)", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "143672554", "name": "Denise Draper"}, {"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "144149089", "name": "Mike Williamson"}], "abstract": null}, {"paperId": "632fe70623e799358233fcac62dd84b80df7534f", "title": "An Asymptotic Analysis of Speedup Learning", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/b978-1-55860-247-2.50022-x?email= or https://doi.org/10.1016/b978-1-55860-247-2.50022-x, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "649c119f36c90c64a5a9d641a3b29995941c397b", "title": "Building Softbots for UNIX (Preliminary Report)", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "2229222", "name": "R. Segal"}], "abstract": null}, {"paperId": "83648d2d1cbaf81700cb563d83b54c61e6c792d4", "title": "An Approach to Planning with Incomplete Information", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "143672554", "name": "Denise Draper"}, {"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "144149089", "name": "Mike Williamson"}], "abstract": null}, {"paperId": "b05bdf97e5ffa43c050ac812ad28a6365144d4b4", "title": "An Approach to Planning with Incomplete Information Appears in KR-92", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "38413017", "name": "S. Hanks"}, {"authorId": "1780531", "name": "Daniel S. Weld"}, {"authorId": "143672554", "name": "Denise Draper"}, {"authorId": "3012739", "name": "N. Lesh"}, {"authorId": "144149089", "name": "Mike Williamson"}, {"authorId": "2099288396", "name": "E. Davis"}, {"authorId": "145068683", "name": "M. Drummond"}, {"authorId": "40359484", "name": "Keiji Kanazawa"}], "abstract": null}, {"paperId": "0c558ecfbf72591ad320740131bf612275c96f8d", "title": "Integrating Efficient Model-Learning and Problem-Solving Algorithms in Permutation Environments", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "2898671", "name": "P. Chalasani"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145721946", "name": "J. Mount"}], "abstract": null}, {"paperId": "36e4364ca1972efbae52eec4037c7e0d6ce7b5ab", "title": "Integrating Abstraction and Explanation-Based Learning in PRODIGY", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "145293454", "name": "Steven Minton"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "73261652536e5f3462335eaa90b9126d62a8687b", "title": "Embedding Decision-Analytic Control in a Learning Architecture", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/0004-3702(91)90008-8?email= or https://doi.org/10.1016/0004-3702(91)90008-8, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8042009c5845a28501c5e1573cc1084480cb4d38", "title": "STATIC: A Problem-Space Compiler for PRODIGY", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "8c57de854745336a77cd4914fdb76190e2a633bd", "title": "PRODIGY: an integrated architecture for planning and learning", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1145/122344.122353?email= or https://doi.org/10.1145/122344.122353, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "143712374", "name": "J. Carbonell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145526918", "name": "Y. Gil"}, {"authorId": "143676491", "name": "R. Joseph"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "145293454", "name": "Steven Minton"}, {"authorId": "1956361", "name": "M. Veloso"}], "abstract": null}, {"paperId": "15ebe13f0a12e51eae08180690ea025fdae45008", "title": "Why PRODIGY/EBL Works", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "178e9e9d1713b9dca1d9dd19b6f0e42827fa3095", "title": "Tractable Decision-Analytic Control", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "2766913aabb151107b28279645b915a3aa86c816", "title": "Explanation-Based Learning: A Problem Solving Perspective", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: Paper or abstract available at https://api.unpaywall.org/v2/10.1016/0004-3702(89)90047-7?email= or https://doi.org/10.1016/0004-3702(89)90047-7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145293454", "name": "Steven Minton"}, {"authorId": "143712374", "name": "J. Carbonell"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "2796674", "name": "D. Kuokka"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145526918", "name": "Y. Gil"}], "abstract": "Abstract This article outlines explanation-based learning (EBL) and its role in improving problem solving performance through experience. Unlike inductive systems, which learn by abstracting common properties from multiple examples, EBL systems explain why a particular example is an instance of a concept. The explanations are then converted into operational recognition rules. In essence, the EBL approach is analytical and knowledge-intensive, whereas inductive methods are empirical and knowledge-poor. This article focuses on extensions of the basic EBL method and their integration with the prodigy problem solving system. prodigy 's EBL method is specifically designed to acquire search control rules that are effective in reducing total search time for complex task domains. Domain-specific search control rules are learned from successful problem solving decisions, costly failures, and unforeseen goal interactions. The ability to specify multiple learning strategies in a declarative manner enables EBL to serve as a general technique for performance improvement. prodigy 's EBL method is analyzed, illustrated with several examples and performance results, and compared with other methods for integrating EBL and problem solving."}, {"paperId": "754529a98c7df45635b0014a68355da8344b9566", "title": "Readings in AI and software engineering: Edited by Grosz, Jones Webber Morgan Kaufman Publishers, Inc., Los Angeles, California, 1986, 602 pp, $26.95, ISBN: 0 934613 12 5", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/0954-1810(89)90006-X?email= or https://doi.org/10.1016/0954-1810(89)90006-X, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "9c3d46debd7d9f27133d19b668c89d23289a0ca5", "title": "Hypothesis Filtering: A Practical Approach to Reliable Learning", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/B978-0-934613-64-4.50047-5?email= or https://doi.org/10.1016/B978-0-934613-64-4.50047-5, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "5ed61e1c641e90d3bb6504a2512943928df4bb90", "title": "Acquiring Effective Search Control Rules: Explanation-Based Learning in the PRODIGY System", "openAccessPdf": {"url": "", "status": "CLOSED", "license": null, "disclaimer": "Notice: The following paper fields have been elided by the publisher: {'abstract'}. Paper or abstract available at https://api.unpaywall.org/v2/10.1016/B978-0-934613-41-5.50016-7?email= or https://doi.org/10.1016/B978-0-934613-41-5.50016-7, which is subject to the license by the author or copyright owner provided with this content. Please go to the source to verify the license and copyright information for your use."}, "authors": [{"authorId": "145293454", "name": "Steven Minton"}, {"authorId": "143712374", "name": "J. Carbonell"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "2796674", "name": "D. Kuokka"}], "abstract": null}, {"paperId": "4cff70adf24e70a2dc88e1c3eedc649a77a65b67", "title": "Explanation-based Learning:a Problem Solving Perspective. Learning Hierarchically Clustered Shared Plan Abstractions as Problem Solving Knowledge with High Utility for Planning. in A. Horz, Editor, Proceed- Ings of Gi-workshop on 'planung Und Konngurierung' Puk, Number 723 in Arbeitspa- 6.2 Related ", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "69388632", "name": "S. Minton"}, {"authorId": "143712374", "name": "J. Carbonell"}, {"authorId": "1745117", "name": "Craig A. Knoblock"}, {"authorId": "2796674", "name": "D. Kuokka"}, {"authorId": "1741101", "name": "Oren Etzioni"}, {"authorId": "145526918", "name": "Y. Gil"}, {"authorId": "1680938", "name": "M. Musen"}, {"authorId": "3109683", "name": "Lawrence M. Fagan"}, {"authorId": "38536083", "name": "D. M. Combs"}, {"authorId": "2083214609", "name": "E. H. Shortliie"}, {"authorId": "143837481", "name": "S. Bergmann"}, {"authorId": "69360276", "name": "Schmalhofer"}, {"authorId": "2080006144", "name": "Bergmann"}, {"authorId": "2766514", "name": "F. Schmalhofer"}, {"authorId": "2080886959", "name": "Cecos"}], "abstract": null}, {"paperId": "7551de62763b77e348712f8025b053236b96c099", "title": "IN S CIENCE AND T ECHNOLOGY", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "47950990", "name": "Amitai Etzioni"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "aa76c4ae41add6ed34496f5882545573fd6bda4c", "title": "2 Extracting Product Features and Opinions from Reviews", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "41192561", "name": "A. Popescu"}, {"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}, {"paperId": "e49901a69f7724cee2733d00e7b1ee9d88b4655b", "title": "Static Ace", "openAccessPdf": {"url": "", "status": null, "license": null}, "authors": [{"authorId": "1741101", "name": "Oren Etzioni"}], "abstract": null}]}