Acquisition and application of contextual role knowledge for...

Data processing: speech signal processing – linguistics – language – Linguistics – Natural language

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

C704S001000, C704S010000

Reexamination Certificate

active

07813916

ABSTRACT:
Coreference resolution is the process of identifying when two noun phrases (NP) refer to the same entity. Two main contributions to computational coreference resolution are made. First, this work contributes a new method for recognizing when an NP is anaphoric. Second, traditional approaches to coreference resolution typically select the most appropriate antecedent by recognizing word similarity, proximity, and agreement in number, gender, and semantic class. This work contributes a new source of evidence that focuses on the roles that an anaphor and antecedent play in particular events or relationships. I show that using contextual role knowledge as part of the coreference resolution process increases the number of anaphors that can be resolved, and I demonstrate an unsupervised method for acquiring contextual role knowledge that does not require an annotated training corpus. A probabilistic model based on the Dempster-Shafer model of evidence is used to incorporate contextual role knowledge with traditional evidence sources.

REFERENCES:
patent: 4661924 (1987-04-01), Okamoto et al.
patent: 4965763 (1990-10-01), Zamora
patent: 4992972 (1991-02-01), Brooks et al.
patent: 5146405 (1992-09-01), Church
patent: 5424947 (1995-06-01), Nagao et al.
patent: 5475587 (1995-12-01), Anick et al.
patent: 5614899 (1997-03-01), Tokuda et al.
patent: 5696916 (1997-12-01), Yamazaki et al.
patent: 5708822 (1998-01-01), Wical
patent: 5799268 (1998-08-01), Boguraev
patent: 5802504 (1998-09-01), Suda et al.
patent: 5844798 (1998-12-01), Uramoto
patent: 5878385 (1999-03-01), Bralich et al.
patent: 5890103 (1999-03-01), Carus
patent: 5901068 (1999-05-01), Batchilo et al.
patent: 5963940 (1999-10-01), Liddy et al.
patent: 6056428 (2000-05-01), Devoino et al.
patent: 6102969 (2000-08-01), Christianson et al.
patent: 6167370 (2000-12-01), Tsourikov et al.
patent: 6202043 (2001-03-01), Devoino et al.
patent: 6304870 (2001-10-01), Kushmerick et al.
patent: 6343266 (2002-01-01), Paul et al.
patent: 6405162 (2002-06-01), Segond et al.
patent: 6859931 (2005-02-01), Cheyer et al.
patent: 7490092 (2009-02-01), Sibley et al.
patent: 2003/0149586 (2003-08-01), Chen et al.
patent: 2004/0078750 (2004-04-01), Frank
patent: 2004/0128615 (2004-07-01), Carmel et al.
patent: 2005/0086592 (2005-04-01), Polanyi et al.
patent: 2005/0216443 (2005-09-01), Morton et al.
patent: WO 98/24016 (1998-06-01), None
patent: WO 99/18527 (1999-04-01), None
patent: WO 00/14651 (2000-03-01), None
patent: WO 00/46703 (2000-08-01), None
Carbonell et al., Anaphora Resolution: A Multi-Strategy Approach, Apr. 15, 1988, Proceedings of the 12 conference on Cmputational linguistics, vol. 1, p. 96-101.
Kehler, Probabilistic Coreference in Information Extraction, 1997, Proceedings of the Second Conference on Empirical Methods in Natural Language Processing, p. 1-11.
Altmann, Thematic Role Assignment in Context, 1999, Journal of Memory and Lnaguage 41, pp. 124-145.
Modjeska, Lexical and grammatical role constraints in resolving other-anaphora, 2002, Citeseer, Proc. of DAARC 2002, pp. 129-134.
Baldwin, CogNIAC: high precision coreference with limited knowledge and linguistic resources, 1997, ACL, Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pp. 38-45.
Ng et al., Improving Machine Learning Approaches to Coreference Resolution, Jul. 2002, ACL, Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 104-111.
Riloff, Ellen, “Automatically Constructing A Dictionary for Information Extraction Tasks”, Proceedings of the Eleventh National Conference on Artificial Intelligence (1993), pp. 811-816.
Riloff, Ellen, “Automatically Generating Extraction Patterns from Untagged Text”, Proceedings of the Thirtheenth National Conference on Artificial Intelligence (1995), pp. 1044-1049.
Riloff, Ellen, “Using Learned Extraction Patterns for Text Classification”, Connectionist, Statistical and Symbolic. Approaches to Learning for Natural Language Processing (1996), pp. 275-289.
Riloff, Ellen, “Little Words Can Make a Big Difference for Text Classification”, Proceedings of the 18thAnnual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 130-136, 1995.
Riloff, Ellen and Schmelzenbach, Mark, “An Empirical Approach to Conceptual Case Frame Acquisition”, Proceedings of the Sixth Workshop on Very Large Corpora (1998), 8 pages.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Acquisition and application of contextual role knowledge for... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Acquisition and application of contextual role knowledge for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Acquisition and application of contextual role knowledge for... will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-4222049

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.