Browsing by Author "Wu, Dian-Song"

Now showing 1 - 5 of 5

A case-based reasoning approach to zero anaphora resolution in Chinese texts
(2006)
Wu, Dian-Song
;
Liang, Tyne
;
資訊工程學系
;
Department of Computer Science
Anaphora is a common phenomenon in discourses as well as an important research issue in the applications of natural language processing. In this paper, both intra-sentential and inter-sentential zero anaphora in Chinese texts are addressed. Unlike general rule-based approaches, our resolution method is embedded with a case-based reasoning mechanism which has the benefit of knowledge acquisition if the case size varies. In addition, the presented approach employs informative features with the help of two outer knowledge resources. Compared to rule-based approaches, our resolution to 1047 zero anaphora instances achieved 82% recall and 77% precision.
Chinese Pronominal Anaphora Resolution Using Lexical Knowledge and Entropy-Based Weight
(2008-11-01)
Wu, Dian-Song
;
Liang, Tyne
;
資訊工程學系
;
Department of Computer Science
Pronominal anaphors are commonly observed in written texts. In this article, effective Chinese pronominal anaphora resolution is addressed by using lexical knowledge acquisition and salience measurement. The lexical knowledge acquisition is aimed to extract more semantic features, such as gender, number, and collocate compatibility by employing multiple resources. The presented salience measurement is based on entropy-based weighting on selecting antecedent candidates. The resolution is justified with a real corpus and compared with a rule-based model. Experimental results by five-fold cross-validation show that our approach yields 82.5% success rate on 1343 anaphoric instances. In comparison with a general rule-based approach, the performance is improved by 7%.
Improving Chinese pronominal anaphora resolution by extensive feature representation and confidence estimation
(2008)
Liang, Tyne
;
Wu, Dian-Song
;
資訊工程學系
;
Department of Computer Science
Pronominal 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.
Improving Definite Anaphora Resolution by Effective Weight Learning and Web-Based Knowledge Acquisition
(2011-03-01)
Wu, Dian-Song
;
Liang, Tyne
;
資訊工程學系
;
Department of Computer Science
In this paper, effective Chinese definite anaphora resolution is addressed by using feature weight learning and Web-based knowledge acquisition. The presented salience measurement is based on entropy-based weighting on selecting antecedent candidates. The knowledge acquisition model is aimed to extract more semantic features, such as gender, number, and semantic compatibility by employing multiple resources and Web mining. The resolution is justified with a real corpus and compared with a classification-based model. Experimental results show that our approach yields 72.5% success rate on 426 anaphoric instances. In comparison with a general classification-based approach, the performance is improved by 4.7%.
Zero anaphora resolution by case-based reasoning and pattern conceptualization
(2009-05-01)
Wu, Dian-Song
;
Liang, Tyne
;
資訊工程學系
;
Department of Computer Science
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.