完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWu, Dian-Songen_US
dc.contributor.authorLiang, Tyneen_US
dc.date.accessioned2014-12-08T15:09:32Z-
dc.date.available2014-12-08T15:09:32Z-
dc.date.issued2009-05-01en_US
dc.identifier.issn0957-4174en_US
dc.identifier.urihttp://dx.doi.org/10.1016/j.eswa.2008.09.065en_US
dc.identifier.urihttp://hdl.handle.net/11536/7280-
dc.description.abstractEffective anaphora resolution is helpful to many applications of natural language processing such as machine translation, summarization and question answering. In this paper, a novel resolution approach is proposed to tackle zero anaphora, which is the most frequent type of anaphora shown in Chinese texts. Unlike most of the previous approaches relying on hand-coded rules, our resolution is mainly constructed by employing case-based reasoning and pattern conceptualization. Moreover, the resolution is incorporated with the mechanisms to identify cataphora and non-antecedent instances so as to enhance the resolution performance. Compared to a general rule-based approach, the proposed approach indeed improves the resolution performance by achieves 78% recall and 79% precision on solving 1051 zero anaphora instances in 382 narrative texts. (C) 2008 Elsevier Ltd. All rights reserved.en_US
dc.language.isoen_USen_US
dc.subjectZero anaphora resolutionen_US
dc.subjectCase-based reasoningen_US
dc.subjectConceptual patternsen_US
dc.subjectKnowledge resourcesen_US
dc.titleZero anaphora resolution by case-based reasoning and pattern conceptualizationen_US
dc.typeArticleen_US
dc.identifier.doi10.1016/j.eswa.2008.09.065en_US
dc.identifier.journalEXPERT SYSTEMS WITH APPLICATIONSen_US
dc.citation.volume36en_US
dc.citation.issue4en_US
dc.citation.spage7544en_US
dc.citation.epage7551en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000264528600027-
dc.citation.woscount3-
顯示於類別:期刊論文


文件中的檔案:

  1. 000264528600027.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。