臺灣博碩士論文加值系統

指代問題是一個存在於語段中的普遍現象，同時也是自然語言處理應用上的一個重要議題。傳統的做法上是利用語法、語意及語用上的線索來辨識指代詞所指的先行詞。在本篇論文中，我們利用電子詞彙資源－詞網所建構而成的知識與經驗法則來消解英文語段中產生的指代現象，找出在單句中或句子與句子間的參考關係。分析本文前後名詞和動詞間的階層關係以取得生命實體訊息，同時藉由辨識語段中的生命實體及虛詞的出現來提升整體消解結果的準確性。

Anaphora is a common phenomenon in discourses as well as an important research issue in the applications of natural language processing. Traditionally, anaphora resolution systems rely on syntactic, semantic or pragmatic clues to identify the antecedent of an anaphor. In this thesis, the resolution of anaphora is achieved by employing WordNet ontology and heuristic rules. The proposed system identifies both intra-sentential and inter-sentential antecedents of anaphors. Information about animacy is obtained by analyzing the hierarchical relation of nouns and verbs in the surrounding context. The identification of animacy entities and pleonastic-it usage in English discourses are employed to promote the resolution accuracy.

Contents
Abstract (in Chinese) i
Abstract (in English) ii
Acknowledgement iii
Contents iv
List of Figures vi
List of Tables vii
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Definition 2
1.2.1 Anaphora Categories 2
1.2.2 Intra-sentential and Inter-sentential Anaphora 4
1.3 Anaphora vs. Coreference 5
1.4 Thesis Synopsis and Goal 7
Chapter 2 Related Works 8
2.1 Syntax-based Strategy 8
2.2 Semantic-based Strategy 10
2.3 Statistical-based Strategy 11
2.4 Alternative Strategy 12
Chapter 3 System Architecture 16
3.1 Proposed System Overview 16
3.2 Main Components 16
3.2.1 POS Tagging 16
3.2.2 NP Finder 18
3.2.3 Pleonastic-it Module 20
3.2.4 Number Agreement 22
3.2.5 Gender Agreement 22
3.2.6 Animacy Agreement 23
3.2.7 Heuristic Rules 28
3.2.8 Data Structure 31
3.3 The Brown Corpus 31
3.4 The Resolution Procedure 32
Chapter 4 System Graphic User Interface 35
4.1 Function Description 36
Chapter 5 Experimental Results and Analysis 43
5.1 Experimental Environment 43
5.2 Identification of Animacy Entities 43
5.3 Evaluation 45
5.3.1 Pleonastic-it Analysis 48
5.3.2 Reference Distance 48
5.3.3 Experiment Result 49
Chapter 6 Conclusion and Future Work 50
References 51

Aarts Jan, Henk Barkema and Nelleke Oostdijk (1997), “The TOSCA-ICLE Tagset: Tagging Manual”, TOSCA Research Group for Corpus Linguistics.
Baldwin, Breck (1997), “CogNIAC: high precision coreference with limited knowledge and linguistic resources”, Proceedings of the ACL'97/EACL'97 workshop on Operational factors in practical, robust anaphora resolution, pp. 38-45.
Bontcheva, Kalina, Marin Dimitrov, Diana Maynard and Valentin Tablan (2002), “Shallow Methods for Named Entity Coreference Resolution”, Proceedings of TRAITEMENT AUTOMATIQUE DES LANGUES NATURELLES (TALN), pp. 24-32.
Cardie, Claire and Kiri Wagstaff (1999), “Noun Phrase Coreference as Clustering”, Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Very Large Corpora.
Chen, Kuang-hua and Hsin-Hsi Chen (1994), “Extracting Noun Phrases from Large-Scale Texts: A Hybrid Approach and Its Automatic Evaluation”, Proceedings of the 32nd ACL Annual Meeting, 1994, pp. 234-241.
Dagan, Ido and Alon Itai (1990), “Automatic processing of large corpora for the resolution of anaphora references”, Proceedings of the 13th International Conference on Computational Linguistics (COLING'90), Vol. III, 1-3, Helsinki, Finland.
Denber, Michel (1998), “Automatic resolution of anaphora in English”, Technical report, Eastman Kodak Co.
Evans, Richard and Constantin Orasan (2000), “Improving anaphora resolution by identifying animate entities in texts”, In Proceedings of DAARC-2000.
Ge, Niyu, John Hale and Eugene Charniak (1998), “A Statistical Approach to Anaphora Resolution”, Proceedings of the Sixth Workshop on Very Large Corpora (COLING-ACL98), pp.161-170.
Kennedy, Christopher and Branimir Boguraev (1996), “Anaphora for everyone:
Pronominal anaphora resolution without a parser”, Proceedings of the 16th International Conference on Computational Linguistics, pp.113-118.
Lappin, Shalom and Herbert Leass (1994), “An Algorithm for Pronominal Anaphora
Resolution”, Computational Linguistics, Volume 20, Part 4, pp. 535-561.
Miller, George (1993), “Nouns in WordNet: A Lexical Inheritance System”, Journal of Lexicography, pp. 245-264.
Mitkov, Ruslan (1998), “Robust pronoun resolution with limited knowledge”, Proceedings of the 18th International Conference on Computational Linguistics (COLING'98)/ACL'98 Conference Montreal, Canada. pp. 869-875.
Mitkov, Ruslan (1999), “Anaphora Resolution: The State of the Art”, Working paper (Based on the COLING'98/ACL'98 tutorial on anaphora resolution)
Mitkov, Ruslan and Catalina Barbu (2001), “Evaluation tool for rule-based anaphora resolution methods”, Proceedings of ACL'01, Toulouse, 2001.
Mitkov, Ruslan, Richard Evans and Constantin Orasan (2002), “A new, fully automatic version of Mitkov's knowledge-poor pronoun resolution method”, In Proceedings of CICLing- 2000, Mexico City, Mexico.
Wang, Ning, Chunfa Yuan, K.F. Wang and Wenjie Li (2002), “Anaphora Resolution in Chinese Financial News for Information Extraction”, Proceedings of 4th World Congress on Intelligent Control and Automation, June 2002, Shanghai, pp.2422-2426.
Yu, Chi-Hsin (2000), “中文資訊擷取環境建構與同指涉問題之研究”, 國立台灣大學資訊工程研究所, 碩士論文