Archive of readings, Fall 2002
5 December 2002: Afra Alishahi and Jane Li lead discussion on:
Hai Leong Chieu and Hwee Tou Ng (2002). ``A maximum entropy approach to information extraction from semi-structured and free text.'' Proceedings, 18th National Conference on Artificial Intelligence (AAAI-2002), Edmonton, 786--791.
Mark Stevenson and Robert Gaizauskas (2000). ``Using corpus-derived name lists for named entity recognition.'' Proceedings of the Sixth Conference on Applied Natural Language Processing and First Conference of the North American Chapter of the Association for Computational Linguistics, Seattle.
Chieu and Ng paper (pdf, 176 Kb) Stevenson and Gaizauskas paper (pdf, 191 Kb)
28 November 2002: Preetam Maloor and Ashkan Gholamzadeh lead discussion on:
Sanda Harabagiu, Dan Moldovan, Marius Pasca, Rada Mihalcea, Mihai Surdeanu, Razvan Bunescu, Roxana Girju, Vasile Rus, and Paul Morarescu (2001). ``The role of lexico-semantic feedback in open-domain textual question-answering''. Proceedings of the 39th Annual Meeting of the Association for Computational Linguistics (ACL-2001), July 2001, Toulouse, France, 274--281.
Ellen Riloff and Michael Thelen (2000). ``A rule-based question answering system for reading comprehension tests.'' ANLP/NAACL-2000 Workshop on Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding Systems, Seattle, WA.
Harabagiu et al. paper (pdf, 100 Kb) Riloff and Thelen paper (pdf, 213 Kb)
21 November 2002: Faye Baron and Afra Alishahi lead discussion on:
Cynthia A. Thompson and Raymond J. Mooney (1999). ``Automatic construction of semantic lexicons for learning natural language interfaces.'' Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), Orlando, FL, July, 1999.
Evelyn Viegas, Boyan Onyshkevych, Victor Raskin, Sergei Nirenburg (1996). ``From submit to submitted via submission: On lexical rules in large-scale lexicon acquisition''. Proceedings, 34th annual meeting of the Association for Computational Linguistics, Santa Cruz.
Thompson and Mooney paper (pdf, 220 Kb) Viegas etal paper (pdf, 777 Kb)
14 November 2002: Ken Hoetmer and Bob Swier lead discussion on:
Paul Clough, Robert Gaizauskas, Scott Piao and Yorick Wilks (2002). ``METER: MEasuring TExt Reuse''. Proceedings of the 40th meeting of the Association for Computational Linguistics (ACL-02), Philadelphia, 152--159.
Byron, Donna (2002) ``Resolving pronominal reference to abstract entities''. Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Philadelphia.
Clough paper (pdf, 1.29 Mb) Clough paper (ps, 649 Kb) Byron paper (pdf, 271 Kb)
7 November 2002: Guest: Shalom Lappin (King's College London) presents his work:
Christian Ebert, Shalom Lappin, Howard Gregory, and Nicolas Nicolov (2001). ``Generating full paraphrases of fragments in a dialogue interpretation system.'' Revised version of a paper in Proceedings of the Second SIGdial Workshop on Discourse and Dialogue, Aalborg, Denmark.
The paper (pdf, 128 Kb)
31 October 2002: Guest: Philippe Langlais (Université de Montréal) will talk about his recent work:
Philippe Langlais and Michel Simard (2002). ``Merging example-based and statistical machine translation: An experiment.'' Proceedings of the Fifth Conference of Association for Machine Translation in the Americas (AMTA), Tiburon, California, October 8-12, pp. 104--114.
Philippe Langlais (2002). ``Improving a general-purpose statistical translation engine by terminological lexicons.'' Proceedings of the 2nd International Workshop on Computational Terminology (COMPUTERM), Taipei, Taiwan, pp. 1--7.
Langlais and Simard paper (pdf, 205 Kb) Langlais paper (pdf, 193 Kb)
24 October 2002: Preetam Maloor and Bob Swier lead discussion on:
Müller, Christoph; Rapp, Stefan; Strube, Michael (2002). ``Applying co-training to reference resolution.'' Proceedings of the 40th annual meeting of the Association for Computational Linguistics, Philadelphia.
Riloff, Ellen and Jones, Rosie (1999). ``Learning dictionaries for information extraction by multi-level bootstrapping.'' Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI-99), 474-479.
Müller paper (pdf, 97 Kb) Riloff paper (pdf, 170 Kb)
17 October 2002: Kwangseob Shim leads discussion on:
Kwangseob Shim, ``Segmentation of Compound Nouns using Composite Mutual Information'', Proceedings of 3rd Chinese-Korea Joint Symposium on Oriental Language Processing and Character Recognition, pp.106-113, 1999.
Kwangseob Shim and Jaehyung Yang, ``MACH: A Supersonic Korean Morphological Analyzer'', Proceedings of the 19th International Conference on Computational Linguistics (COLING-2002), pp.939-945, 2002.
1999 paper (pdf, 185 Kb) 2002 paper (pdf, 218 Kb)
10 October 2002: Helena Hong Gao leads discussion on:
Hong Gao (2001). ``A specification system for measuring relationship among near-synonyms of physical action verbs.'' Second Workshop on Chinese Lexical Semantics, Peking University, May 14-18, 2001. Part of the content appeared in Chapter 4 of her The Physical Foundation of the Patterning of Physical Action Verbs, Lund University Press, 2001.
Gao paper (pdf, 835 Kb)
3 October 2002: Amber Wilcox-O'Hearn and Faye Baron lead discussion on:
Vasileios Hatzivassiloglou and Kathleen McKeown (1997). ``Predicting the semantic orientation of adjectives.'' Proceedings, 35th annual meeting of the Association for Computational Linguistics, Madrid.
Peter Turney (2002). ``Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews.'' Proceedings, 40th Annual Meeting of the Association for Computational Linguistics (ACL'02), Philadelphia, Pennsylvania, 417--424.
Hatzivassiloglou paper (pdf, 752 Kb) Turney paper (pdf, 57 Kb)
26 September 2002: Ashkan Gholamzadeh and Yun Niu lead discussion on:
Ryen White, Ian Ruthven, and Joemon Jose (2002). ``Finding relevant documents using top ranking sentences: An evaluation of two alternative schemes.'' Proceedings, 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Tampere, August 2002, pages 57--64.
Seung-Taek Park, David Pennock, C. Lee Giles, and Robert Krovetz (2002). ``Analysis of lexical signatures for finding lost or related documents.'' Proceedings, 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Tampere, August 2002, pages 11--18.
White paper (pdf, 260 Kb) Park paper (pdf, 388 Kb) (NEW VERSION).
19 September 2002: Jane Li leads discussion on:
Li Jianhua and Wang Xiaolong (to appear). ``Combine trigram and automatic weight distribution in Chinese spelling error correction.''
Li paper (pdf, 2.57 Mb)
12 September 2002: Graeme Hirst leads discussion on:
Yu-Sheng Lai and Chung-Hsien Wu (2002). ``Meaningful term extraction and discriminative term selection in text categorization via unknown-word methodology.'' ACM Transactions on Asian Language Information Processing, 1(1), 34--64.
Lai paper (pdf, 900 Kb) Slides from talk, 2-up format (pdf, 66Kb)