An Entity Based Model for Coreference Resolution

Abstract

Previous chapter Next chapter Full AccessProceedings Proceedings of the 2009 SIAM International Conference on Data Mining (SDM)An Entity Based Model for Coreference ResolutionMichael Wick, Aron Culotta, Khashayar Rohanimanesh, and Andrew McCallumMichael Wick, Aron Culotta, Khashayar Rohanimanesh, and Andrew McCallumpp.365 - 376Chapter DOI:https://doi.org/10.1137/1.9781611972795.32PDFBibTexSections ToolsAdd to favoritesExport CitationTrack CitationsEmail SectionsAboutAbstract Recently, many advanced machine learning approaches have been proposed for coreference resolution; however, all of the discriminatively-trained models reason over mentions rather than entities. That is, they do not explicitly contain variables indicating the "canonical" values for each attribute of an entity (e.g., name, venue, title, etc.). This canonicalization step is typically implemented as a post-processing routine to coreference resolution prior to adding the extracted entity to a database. In this paper, we propose a discriminatively-trained model that jointly performs coreference resolution and canonicalization, enabling features over hypothesized entities. We validate our approach on two different coreference problems: newswire anaphora resolution and research paper citation matching, demonstrating improvements in both tasks and achieving an error reduction of up to 62% when compared to a method that reasons about mentions only. Previous chapter Next chapter RelatedDetails Published:2009ISBN:978-0-89871-682-5eISBN:978-1-61197-279-5 https://doi.org/10.1137/1.9781611972795Book Series Name:ProceedingsBook Code:PR133Book Pages:1-1244