Show simple item record

dc.contributor.authorPekar, Viktor
dc.date.accessioned2008-05-23T16:39:51Z
dc.date.available2008-05-23T16:39:51Z
dc.date.issued2008
dc.identifier.citationComputer Speech & Language, 22 (1): 1-16
dc.identifier.issn08852308
dc.identifier.issn10958363
dc.identifier.doi10.1016/j.csl.2007.05.001
dc.identifier.urihttp://hdl.handle.net/2436/27900
dc.description.abstractEvent entailment is knowledge that may prove useful for a variety of applications dealing with inferencing over events described in natural language texts. In this paper, we propose a method for automatic discovery of pairs of verbs related by entailment, such as X buy Y X own Y and appoint X as Y X become Y. In contrast to previous approaches that make use of lexico-syntactic patterns and distributional evidence, the underlying assumption of our method is that the implication of one event by another manifests itself in the regular co-occurrence of the two corresponding verbs within locally coherent text. Based on the analogy with the problem of learning selectional preferences Resnik’s [Resnik, P., 1993. Selection and information: a class-based approach to lexical relationships, Ph.D. Thesis, University of Pennsylvania] association strength measure is used to score the extracted verb pairs for asymmetric association in order to discover the direction of entailment in each pair. In our experimental evaluation, we examine the effect that various local discourse indicators produce on the accuracy of this model of entailment. After that we carry out a direct evaluation of the verb pairs against human subjects’ judgements and extrinsically evaluate the pairs on the task of noun phrase coreference resolution.
dc.language.isoen
dc.publisherElsevier
dc.relation.urlhttp://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6WCW-4NS2GG9-1&_user=1644469&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000054077&_version=1&_urlVersion=0&_userid=1644469&md5=1476e51eca3b92da92fe97d9673ae682
dc.subjectLexical semantics
dc.subjectLexical entailment
dc.subjectLocal discourse
dc.subjectCoreference resolution
dc.titleDiscovery of event entailment knowledge from text corpora
dc.typeJournal article
dc.identifier.journalComputer Speech & Language
html.description.abstractEvent entailment is knowledge that may prove useful for a variety of applications dealing with inferencing over events described in natural language texts. In this paper, we propose a method for automatic discovery of pairs of verbs related by entailment, such as X buy Y X own Y and appoint X as Y X become Y. In contrast to previous approaches that make use of lexico-syntactic patterns and distributional evidence, the underlying assumption of our method is that the implication of one event by another manifests itself in the regular co-occurrence of the two corresponding verbs within locally coherent text. Based on the analogy with the problem of learning selectional preferences Resnik’s [Resnik, P., 1993. Selection and information: a class-based approach to lexical relationships, Ph.D. Thesis, University of Pennsylvania] association strength measure is used to score the extracted verb pairs for asymmetric association in order to discover the direction of entailment in each pair. In our experimental evaluation, we examine the effect that various local discourse indicators produce on the accuracy of this model of entailment. After that we carry out a direct evaluation of the verb pairs against human subjects’ judgements and extrinsically evaluate the pairs on the task of noun phrase coreference resolution.


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record