Zero anaphora resolution by case-based reasoning and pattern conceptualization
顯示簡易詮釋資料 統計資料| 欄位 | 內容 | 語言 |
|---|---|---|
dc.citation.epage |
7551 | en_US |
dc.citation.issue |
4 | en_US |
dc.citation.spage |
7544 | en_US |
dc.citation.volume |
36 | en_US |
dc.citation.woscount |
3 | |
dc.contributor.author |
Wu, Dian-Song | en_US |
dc.contributor.author |
Liang, Tyne | en_US |
dc.contributor.department |
資訊工程學系 | zh_TW |
dc.contributor.department |
Department of Computer Science | en_US |
dc.date.accessioned |
2014-12-08T15:09:32Z | |
dc.date.available |
2014-12-08T15:09:32Z | |
dc.date.issued |
2009-05-01 | en_US |
dc.description.abstract |
Effective 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.identifier.doi |
10.1016/j.eswa.2008.09.065 | en_US |
dc.identifier.issn |
0957-4174 | en_US |
dc.identifier.journal |
EXPERT SYSTEMS WITH APPLICATIONS | en_US |
dc.identifier.uri |
http://dx.doi.org/10.1016/j.eswa.2008.09.065 | en_US |
dc.identifier.uri |
https://ir.lib.nycu.edu.tw/handle/11536/7280 | |
dc.identifier.wosnumber |
WOS:000264528600027 | |
dc.language.iso |
en_US | en_US |
dc.subject |
Zero anaphora resolution | en_US |
dc.subject |
Case-based reasoning | en_US |
dc.subject |
Conceptual patterns | en_US |
dc.subject |
Knowledge resources | en_US |
dc.title |
Zero anaphora resolution by case-based reasoning and pattern conceptualization | en_US |
dc.type |
Article | en_US |
檔案
- 000264528600027.pdf (356.5 KB, Adobe PDF)
所屬典藏: 期刊論文