A Learning Based Model for Chinese Co-reference Resolution by Mining Contextual Evidence
This paper presents a learning based model for Chinese co-reference resolution, in which diverse contextual features are explored inspired by related linguistic theory. Our main motivation is to try to boost the co-reference resolution performance only by leveraging multiple shallow syntactic and semantic features, which can escape from tough problems such as deep syntactic and semantic structural analysis. Also, reconstruction of surface features based on contextual semantic similarity is conducted to approximate the syntactic and semantic parallel preferences in resolution linguistic theories. Furthermore, we consider two classifiers in the machine learning framework for the co-reference resolution, and performance comparison and combination between them are conducted and investigated. We experimentally evaluate our approaches on standard ACE (Automatic Content Extraction) corpus with promising results.
KeywordsSupport Vector Machine Maximum Entropy Noun Phrase Contextual Feature Baseline System
Unable to display preview. Download preview PDF.
- 1.Mitkov, R.: Anaphora Resolution. Longman, New York (2002)Google Scholar
- 2.NIST,The Official Evaluation Plan for the ACE 2005 Evaluation (2005)Google Scholar
- 3.Ng, V., Cardie, C.: Improving Machine Learning Approaches to coreference resolution. In: Proc. of the ACL 2002, pp. 104–111 (2002)Google Scholar
- 5.Vilain, M., Burger, J., Aberdeen, J., Connolly, D., Hirschman, L.: A Model-Theoretic Coreference Soring Scheme. In: Proc. of MUC-6, pp. 45–52 (1995)Google Scholar
- 6.Ng, V.: Machine Learning for Coreference Resolution: From Local Classification to Global Ranking. In: Proceedings of ACL 2005, Ann Arbor, MI, June 2005, pp. 157–164 (2005)Google Scholar
- 7.Iida, R., Inui, K., Takamura, H., Matsumoto, Y.: Incorporating contextual cues in trainable models for coreference resolution. In: Proc. of the EACL2003 Workshop on the Computational Treatment of Anaphora, pp. 23–30 (2003)Google Scholar
- 8.Liu, Q., Li, S.: Word Similarity Computing Based on How-net. Computational Linguistics and Chinese Language Processing 7(2), 59–76 (2002)Google Scholar
- 10.Strube, M., Rapp, S., Muller, C.: The Influence of Minimum Edit Distance on Reference Resolution. In: Proc. of EMNLP 2002, pp. 312–319 (2002)Google Scholar
- 11.Florian, R., Hassan, H., Ittycheriah, A., Jing, H., Kambhatla, N., Luo, X., Nicolov, N., Roukos, S.: A statistical model for multilingual entity detection and tracking. In: Proc. of HLT/NAACL 2004, Boston Massachusetts, USA, pp. 1–8 (2004)Google Scholar
- 12.Bryant, J.: Combining Feature Based and Semantic Information for Co-reference Resolution. Research report at U.C. Berkeley and ICSI (2004)Google Scholar
- 13.Jurafsky, D., Martin, J.H.: Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice-Hall, Englewood Cliffs (2000)Google Scholar