Full metadata record
DC FieldValueLanguage
dc.contributor.authorLiang, Tyneen_US
dc.contributor.authorWu, Dian-Songen_US
dc.date.accessioned2014-12-08T15:48:55Z-
dc.date.available2014-12-08T15:48:55Z-
dc.date.issued2008en_US
dc.identifier.isbn978-3-540-85286-5en_US
dc.identifier.issn0302-9743en_US
dc.identifier.urihttp://hdl.handle.net/11536/32531-
dc.description.abstractPronominal anaphora resolution denotes antecedent identification for anaphoric pronouns expressed in discourses. Effective resolution relies on the kinds of features to be concerned and how they are appropriately weighted at antecedent identification. In this paper, a rich feature set including the innovative discourse features are employed so as to resolve those commonly-used Chinese pronouns in modem Chinese written texts. Moreover, a maximum-entropy based model is presented to estimate the confidence for each antecedent candidate. Experimental results show that our method achieves 83.5% success rate which is better than those obtained by rule-based and SVM-based methods.en_US
dc.language.isoen_USen_US
dc.subjectpronominal anaphora resolutionen_US
dc.subjectmaximum entropy modelen_US
dc.subjectChineseen_US
dc.subjectdiscourseen_US
dc.titleImproving Chinese pronominal anaphora resolution by extensive feature representation and confidence estimationen_US
dc.typeProceedings Paperen_US
dc.identifier.journalADVANCES IN NATURAL LANGUAGE PROCESSING, PROCEEDINGSen_US
dc.citation.volume5221en_US
dc.citation.spage296en_US
dc.citation.epage302en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000258935200028-
Appears in Collections:Conferences Paper