Abstract
Chinese zero pronoun (ZP) resolution plays a critical role in discourse analysis. Different from traditional mention to mention approaches, this paper proposes a chain to chain approach to improve the performance of ZP resolution from three aspects. Firstly, consecutive ZPs are clustered into coreferential chains, each working as one independent anaphor as a whole. In this way, those ZPs far away from their overt antecedents can be bridged via other consecutive ZPs in the same coreferential chains and thus better resolved. Secondly, common noun phrases (NPs) are automatically grouped into coreferential chains using traditional approaches, each working as one independent antecedent candidate as a whole. Then, ZP resolution is made between ZP coreferential chains and common NP coreferential chains. In this way, the performance can be much improved due to the effective reduction of search space by pruning singletons and negative instances. Finally, additional features from ZP and common NP coreferential chains are employed to better represent anaphors and their antecedent candidates, respectively. Comprehensive experiments on the OntoNotes corpus show that our chain to chain approach significantly outperforms the state-of-the-art mention to mention approaches. To our knowledge, this is the first work to resolve zero pronouns in a chain to chain way.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A corpus study of the OntoNotes corpus reveals that the case containing more than three consecutive ZPs occupies less than 1%. The proportion of three consecutive ZPs is about 5.8%. The case of two consecutive ZPs occupies about 14.3%. The case of just one ZP occupies the most.
- 2.
If the CA and the ZP are in the same sentence, the value is 0; if they are one sentence apart, the value is 1; and so on.
- 3.
- 4.
References
Chen, C., Ng, V.: Chinese zero pronoun resolution: a joint unsupervised discourse-aware model rivaling state-of-the-art resolvers. In: Proceedings of ACL 2015, pp. 320–326. Association for Computational Linguistics (2005)
Chen, C., Ng, V.: Chinese zero pronoun resolution: a unsupervised approach combining ranking and integer linear programming. In: Proceedings of AAAI 2014, pp. 1622–1628 (2014)
Chen, C., Ng, V.: Chinese zero pronoun resolution: an unsupervised probabilistic model rivaling supervised resolvers. In: Proceedings of EMNLP 2014, pp. 763–774. Association for Computational Linguistics (2014)
Chen, C., Ng, V.: Chinese zero pronoun resolution: some recent advances. In: Proceedings of EMNLP 2010, pp. 1360–1365. Association for Computational Linguistics (2010)
Chen, C., Ng, V.: Chinese zero pronoun resolution with deep neural networks. In: Proceedings of ACL 2016, pp. 778–788. Association for Computational Linguistics (2016)
Denis, P., Baldridge, J.: Specialized models and ranking for coreference resolution. In: Proceedings of EMNLP 2008, pp. 660–669. Association for Computational Linguistics (2008)
Kong, F., Zhou, G.: A clause-level hybrid approach to Chinese empty element recovery. In: Proceedings of IJCAI 2013, pp. 2113–2119 (2013)
Kong, F., Zhou, G.: A tree kernel-based unified framework for Chinese zero anaphora resolution. In: Proceedings of EMNLP 2010, pp. 882–891. Association for Computational Linguistics (2010)
Lee, H., Chang, A., Peirsman, Y., Chambers, N., Surdeanu, M., Jurafsky, D.: Deterministic coreference resolution based on entiy-centric, precision-ranked rules. Comput. Linguist. 39, 885–916 (2013)
Moosavi, N.S., Strube, M.: Search space pruning: a simple solution for better coreference resolvers. In: Proceedings of NAACL 2016, pp. 1005–1011. Association for Computational Linguistics (2016)
Yang, X., Su, J., Lang, J., Tan, C.L., Liu, T., Li, S.: An entity-mention model for coreference resolution with inductive logic programming. In: Proceedings of ACL 2008, pp. 843–851. Association for Computational Linguistics (2008)
Yang, X., Zhou, G., Su, J., Tan, C.L.: Coreference resolution using competition learning approach. In: Proceedings of ACL 2013, pp. 176–183. Association for Computational Linguistics (2013)
Zhao, S., Ng, H.T.: Identification and resolution of Chinese zero pronouns: a machine learning approach. In: Proceedings of EMNLP-CoNLL 2007, pp. 541–550. Association for Computational Linguistics (2007)
Acknowledgements
This work is supported by Key Project 61333018 under the National Natural Science Foundation of China, Project 61472264 and 61673290 under the National Natural Science Foundation of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Fang, K., Guodong, Z. (2018). Chinese Zero Pronoun Resolution: A Chain to Chain Approach. In: Huang, X., Jiang, J., Zhao, D., Feng, Y., Hong, Y. (eds) Natural Language Processing and Chinese Computing. NLPCC 2017. Lecture Notes in Computer Science(), vol 10619. Springer, Cham. https://doi.org/10.1007/978-3-319-73618-1_33
Download citation
DOI: https://doi.org/10.1007/978-3-319-73618-1_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-73617-4
Online ISBN: 978-3-319-73618-1
eBook Packages: Computer ScienceComputer Science (R0)