Show simple item record

dc.contributor.authorOrasan, Constantin
dc.contributor.authorEvans, Richard
dc.date.accessioned2008-05-23T15:45:46Z
dc.date.available2008-05-23T15:45:46Z
dc.date.issued2007
dc.identifier.citationJournal of Artificial Intelligence Research, 29 (2007): 79-103
dc.identifier.issn11076 - 9757
dc.identifier.doi10.1613/jair.2179
dc.identifier.urihttp://hdl.handle.net/2436/27896
dc.description.abstractIn anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.
dc.language.isoen
dc.publisherAmerican Association for Artificial Intelligence
dc.relation.urlhttps://www.jair.org/index.php/jair/article/view/10499
dc.subjectArtificial Intelligence
dc.subjectAnaphora resolution
dc.subjectAnimacy identification
dc.titleNP animacy identification for anaphora resolution
dc.typeJournal article
dc.identifier.journalJournal of Artificial Intelligence Research
html.description.abstractIn anaphora resolution for English, animacy identification can play an integral role in the application of agreement restrictions between pronouns and candidates, and as a result, can improve the accuracy of anaphora resolution systems. In this paper, two methods for animacy identification are proposed and evaluated using intrinsic and extrinsic measures. The first method is a rule-based one which uses information about the unique beginners in WordNet to classify NPs on the basis of their animacy. The second method relies on a machine learning algorithm which exploits a WordNet enriched with animacy information for each sense. The effect of word sense disambiguation on the two methods is also assessed. The intrinsic evaluation reveals that the machine learning method reaches human levels of performance. The extrinsic evaluation demonstrates that animacy identification can be beneficial in anaphora resolution, especially in the cases where animate entities are identified with high precision.


This item appears in the following Collection(s)

Show simple item record