Antecedent selection techniques for high-recall roreference resolution

  • We investigate methods to improve the recall in coreference resolution by also trying to resolve those definite descriptions where no earlier mention of the referent shares the same lexical head (coreferent bridging). The problem, which is notably harder than identifying coreference relations among mentions which have the same lexical head, has been tackled with several rather different approaches, and we attempt to provide a meaningful classification along with a quantitative comparison. Based on the different merits of the methods, we discuss possibilities to improve them and show how they can be effectively combined.
Metadaten
Author:Yannick Versley
URN:urn:nbn:de:hebis:30-1111494
URL:http://www.versley.de/D07-1052.pdf
Parent Title (English):Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, June 28–30, 2007, Prague, Czech Republic
Publisher:Association for Computational Linguistics
Place of publication:Stroudsburg, PA
Document Type:Part of a Book
Language:English
Year of Completion:2007
Year of first Publication:2007
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Release Date:2008/11/04
Page Number:10
First Page:496
Last Page:505
Source:Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 496–505, Prague, June 2007 ; http://www.versley.de/D07-1052.pdf
HeBIS-PPN:207011591
Institutes:keine Angabe Fachbereich / Extern
Dewey Decimal Classification:4 Sprache / 40 Sprache / 400 Sprache
Sammlungen:Linguistik
Linguistik-Klassifikation:Linguistik-Klassifikation: Computerlinguistik / Computational linguistics
Licence (German):License LogoDeutsches Urheberrecht