Kathleen Mckeown
Total Page:16
File Type:pdf, Size:1020Kb
Load more
Recommended publications
-
Human Language Technologies 2007: the Conference of the North American Chapter of the Association for Computational Linguistics
NAACL HLT 2007 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics Proceedings of the Main Conference Candace Sidner, General Chair Tanja Schultz, Matthew Stone, and ChengXiang Zhai Program Committee Chairs 22–27 April 2007 Rochester, New York, USA Production and Manufacturing by Omnipress Inc. 2600 Anderson Street Madison, WI 53704 c 2007 The Association for Computational Linguistics Order copies of this and other ACL proceedings from: Association for Computational Linguistics (ACL) 209 N. Eighth Street Stroudsburg, PA 18360 USA Tel: +1-570-476-8006 Fax: +1-507-476-0860 [email protected] ii We Thank Our Sponsors iii iv Preface from the General Chair This year the annual conference organized by the North American chapter of the Association for Computational Linguistics (NAACL) has undergone a name change to NAACL HLT. This change reflects the integral part that all of Human Language Technology plays in the NAACL. It is symbolic of the focus of the conference, which is represented by the collection of submitted and accepted papers. They span our community’s emphasis on speech processing, information retrieval and language processing techniques and applications. The yearly NAACL conference is always the result of the volunteer contributions of a great many people from the NAACL community who put in many hours to make the conference possible. Most of the sub- committees of the organizing committee include researchers from the areas of language processing, speech processing and information retrieval, again reflecting the diversity of expertise and interests in the NAACL world. Each year the general chair calls on a new group of members to serve as the organizing committee. -
Kathleen Mckeown
Kathleen McKeown Department of Computer Science Columbia University New York, NY. 10027 U.S.A. Phone: 212-939-7118 Fax: 212-666-0140 email: [email protected] website: http://www.cs.columbia.edu/ kathy Current position Henry and Gertrude Rothschild Professor of Computer Science, Columbia University, New York Research Interests Computational Linguistics/Natural-Language Processing: Text Summarization; Language Genera- tion; Social Media Analysis; Open-ended question answering; Sentiment Analysis Education 1982 Ph.D., Computer and Information Science, University of Pennsylvania 1979 M.S., Computer and Information Science, University of Pennsylvania 1976 A.B., Comparative Literature, Brown University Appointments held 2012-2018 Founding Director, Columbia Data Science Institute 2011-2012 Vice Dean for Research, School of Engineering and Applied Science 2005-present Henry and Gertrude Rothschild Professor of Computer Science, Columbia University 1997-present Professor, Columbia University 7/2003-12/2003 Acting Chair, Department of Computer Science, Columbia University 1997-2002 Chair, Department of Computer Science, Columbia University 1987-1997 Associate Professor, Columbia University 1982-1987 Assistant Professor, Columbia University Honors & awards 2016 Keynote Speaker, International Semantic Web Conference, Kobe, Japan 20162014 Grace Hopper Distinguished Lecture, University of Pennsylvania Philadelphia, Pa., Nov. 2016. Distin- guished Lecturer, University of Edinburgh, Launch of the Centre for Doctoral Training in Data Science, Edinburgh, -
An Empirical Study of References to People in News Summaries
Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries ∗ Advaith Siddharthan University of Aberdeen ∗∗ Ani Nenkova University of Pennsylvania † Kathleen McKeown Columbia University Although there has been much theoretical work on using various information status distinctions to explain the form of references in written text, there have been few studies that attempt to automatically learn these distinctions for generating references in the context of computer- regenerated text. In this article, we present a model for generating references to people in news summaries that incorporates insights from both theory and a corpus analysis of human written summaries. In particular, our model captures how two properties of a person referred to in the summary—familiarity to the reader and global salience in the news story—affect the content and form of the initial reference to that person in a summary. We demonstrate that these two distinctions can be learned from a typical input for multi-document summarization and that they can be used to make regeneration decisions that improve the quality of extractive summaries. 1. Introduction News reports, and consequently news summaries, contain frequent references to the people who participate in the reported events. Generating referring expressions to people in news summaries is a complex task, however, especially in a multi-document summarization setting where different documents can refer to the same person in different ways. One issue is that the generator has to work with textual input as opposed to closed-domain semantic representations. More importantly, generating references to people involves issues not generally considered in the referring expression literature. -
Information Status Distinctions and Referring Expressions: an Empirical Study of References to People in News Summaries
University of Pennsylvania ScholarlyCommons Departmental Papers (CIS) Department of Computer & Information Science 3-25-2011 Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries Advaith Siddharthan University of Aberdeen Ani Nenkova Univesity of Pennsylvania, [email protected] Kathleen McKeown Columbia University Follow this and additional works at: https://repository.upenn.edu/cis_papers Part of the Computational Linguistics Commons, and the Computer Sciences Commons Recommended Citation Advaith Siddharthan, Ani Nenkova, and Kathleen McKeown, "Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries", . March 2011. Suggested Citation: Siddharthan, A., Nenkova, A., & McKeown, K. (2011). Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries. Computational Linguistics, 37(4), 811-842. This paper is posted at ScholarlyCommons. https://repository.upenn.edu/cis_papers/492 For more information, please contact [email protected]. Information Status Distinctions and Referring Expressions: An Empirical Study of References to People in News Summaries Abstract Although there has been much theoretical work on using various information status distinctions to explain the form of references in written text, there have been few studies that attempt to automatically learn these distinctions for generating references in the context of computer-regenerated text. In this article, we present a model for generating references to people in news summaries that incorporates insights from both theory and a corpus analysis of human written summaries. In particular, our model captures how two properties of a person referred to in the summary—familiarity to the reader and global salience in the news story—affect the content and form of the initial reference to that person in a summary. -
24406 CRA 2001-Final
24406_CRA 2001-final 9/12/01 3:09 PM Page 3 Computing Res AssociationComputing Comp Re AssociationResearch Associ Com ComputingResearch Asso Res AssociationComputing Comp Re Activities of the AssociationResearch Associ Com ComputingResearch Asso Res AssociationComputing Comp Re AssociationResearch Associ Com ccrraa ComputingResearch Asso Res ComputingResearch Association Research AssociationComputing Comp Re AssociationComputing Computing Research AssociationResearch Associ Com ReseaAssociationrch Association Computing ComputingResearch Asso Res 2 0 0 1 ComputingResearch Association Research ANNUALAssociation ComputingREPORT Comp Re AssociationComputing Computing Research AssociationResearch Associ Com ReseaAssociationrch Association Computing ComputingResearch Asso Res ComputingResearch Association Research AssociationComputing Comp Re AssociationComputing Computing Research AssociationResearch Associ Com ReseaAssociationrch Association Computing ComputingResearch Asso Res ComputingResearch Association Research AssociationComputing Comp Re AssociationComputing Computing Research AssociationResearch Associ Com ReseaAssociationrch Association Computing ComputingResearch Asso Res ComputingResearch Association Research AssociationComputing Comp Re AssociationComputing Computing Research AssociationResearch Associ Com ReseaAssociationrch Association Computing ComputingResearch Asso Res ComputingResearch Association Research AssociationComputing Comp Re 24406_CRA 2001-final 9/12/01 3:09 PM Page 4 search putingesearch mputingiation Message from