Abstract
Chinese zero pronoun (ZP) resolution plays a critical role in discourse analysis. Different from traditional mention-to-mention approaches, this article proposes a chain-to-chain approach to improve the performance of ZP resolution in three aspects. First, 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. Second, common noun phrases (NPs) are automatically grouped into coreferential chains using traditional approaches, each working as one independent antecedent candidate as a whole. That is, those NPs occurring in the same coreferential chain are viewed as one antecedent candidate as a whole, and 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 the search space by pruning singletons and negative instances. Third and 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 V5.0 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.
- Chen Chen and Vincent Ng. 2015. Chinese zero pronoun resolution: A joint unsupervised discourse-aware model rivaling state-of-the-art resolvers. In Proceedings of the ACL. Association for Computational Linguistics, 320--326.Google Scholar
Cross Ref
- Chen Chen and Vincent Ng. 2014. Chinese zero pronoun resolution: An unsupervised approach combining ranking and integer linear programming. In Proceedings of the AAAI. 1622--1628. Google Scholar
Digital Library
- Chen Chen and Vincent Ng. 2014. Chinese zero pronoun resolution: An unsupervised probabilistic model rivaling supervised resolvers. In Proceedings of the EMNLP. Association for Computational Linguistics, 763--774.Google Scholar
Cross Ref
- Chen Chen and Vincent Ng. 2010. Chinese zero pronoun resolution: Some recent advances. In Proceedings of the EMNLP. Association for Computational Linguistics, 1360--1365.Google Scholar
- Chen Chen and Vincent Ng. 2016. Chinese zero pronoun resolution with deep neural networks. In Proceedings of the ACL. Association for Computational Linguistics, 778--788.Google Scholar
Cross Ref
- Tagyoung Chung and Daniel Gildea. 2010. Effects of empty categories on machine translation. In Proceedings of the EMNLP. Association for Computational Linguistics, 636--645. Google Scholar
Digital Library
- S. Converse. 2006. Pronominal Anaphora Resolution in Chinese. Ph.D. Dissertation. University of Pennsylvania, Philadelphia, PA. Google Scholar
Digital Library
- Pascal Denis and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the EMNLP. Association for Computational Linguistics, 660--669. Google Scholar
Digital Library
- Antonio Ferrández and Jesús Peral. 2000. A computational approach to zero-pronouns in Spanish. In Proceedings of the ACL. Google Scholar
Digital Library
- Ryu Iida, Kentaro Inui, and Yuji Matsumoto. 2007. Zero-anaphora resolution by learning rich syntactic pattern features. ACM Trans. Asian Lang. Inf. Process. 6, 4 (2007), 1:1--1:22. Google Scholar
Digital Library
- Ryu Iida, Kentaro Torisawa, Chikara Hashimoto, Jong-Hoon Oh, and Julien Kloetzer. 2015. Intra-sentential zero anaphora resolution using subject sharing recognition. In Proceedings of the EMNLP. Association for Computational Linguistics, 2179--2189.Google Scholar
Cross Ref
- Ryu Iida, Kentaro Torisawa, Jong-Hoon Oh, Canasai Kruengkrai, and Julien Kloetzer. 2016. Intra-sentential subject zero anaphora resolution using multi-column convolutional neural network. In Proceedings of the EMNLP. Association for Computational Linguistics, 1244--1254.Google Scholar
Cross Ref
- Fang Kong and Hwee Tou Ng. 2013. Exploiting zero pronouns to improve Chinese coreference resolution. In Proceedings of the EMNLP. Association for Computational Linguistics, 278--288.Google Scholar
- Fang Kong and Guodong Zhou. 2013. A clause-level hybrid approach to Chinese empty element recovery. In Proceedings of the IJCAI. 2113--2119. Google Scholar
Digital Library
- Fang Kong and Guodong Zhou. 2010. A tree kernel-based unified framework for Chinese zero anaphora resolution. In Proceedings of the EMNLP. Association for Computational Linguistics, 882--891. Google Scholar
Digital Library
- Heeyoung Lee, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computat. Ling. 39, 4 (2013), 885--916. Google Scholar
Digital Library
- Charles N. Li and Sandra A. Thompson. 1979. Third-person pronouns and zero-anaphora in Chinese discourse. Synt. Semant., Vol. 12. 311--335.Google Scholar
- Junhui Li, Muhua Zhu, Wei Lu, and Guodong Zhou. 2015. Improving semantic parsing with enriched synchronous context-free grammar. In Proceedings of the EMNLP. 1455--1465.Google Scholar
Cross Ref
- Wendan Li. 2004. Topic chains in Chinese discourse. Discourse Proc., Vol. 37. 25--45.Google Scholar
Cross Ref
- Ting Liu, Yiming Cui, Qingyu Yin, Wei-Nan Zhang, Shijin Wang, and Guoping Hu. 2017. Generating and exploiting large-scale pseudo training data for zero pronoun resolution. In Proceedings of the ACL (Volume 1: Long Papers). Association for Computational Linguistics, 102--111.Google Scholar
Cross Ref
- Nafise Sadat Moosavi and Michael Strube. 2016. Search space pruning: A simple solution for better coreference resolvers. In Proceedings of the NAACL. Association for Computational Linguistics, 1005--1011.Google Scholar
Cross Ref
- Yu Zhang, Ting Liu, Qingyu Yin, Weinan Zhang. 2017. A deep neural network for Chinese zero pronoun resolution. In Proceedings of the IJCAI. 3322--3328. Google Scholar
Digital Library
- Sudha Rao, Allyson Ettinger, Hal Daumé III, and Philip Resnik. 2015. Dialogue focus tracking for zero pronoun resolution. In Proceedings of the NAACL-HLT. Association for Computational Linguistics, 494--503.Google Scholar
- Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computat. Ling. 27, 4 (2001), 521--544. Google Scholar
Digital Library
- Bing Xiang, Xiaoqiang Luo, and Bowen Zhou. 2013. Enlisting the ghost: Modeling empty categories for machine translation. In Proceedings of the ACL. Association for Computational Linguistics, 822--831.Google Scholar
- Xiaofeng Yang, Jian Su, Jun Lang, Chew Lim Tan, Ting Liu, and Sheng Li. 2008. An entity-mention model for coreference resolution with inductive logic programming. In Proceedings of the ACL. Association for Computational Linguistics, 843--851.Google Scholar
- Xiaofeng Yang, Guodong Zhou, Jian Su, and Chew Lim Tan. 2013. Coreference resolution using competition learning approach. In Proceedings of the ACL. Association for Computational Linguistics, 176--183. Google Scholar
Digital Library
- Yaqin Yang, Yalin Liu, and Nianwen Xue. 2015. Recovering dropped pronouns from Chinese text messages. In Proceedings of the ACL. Association for Computational Linguistics, 309--313.Google Scholar
Cross Ref
- Qingyu Yin, Yu Zhang, Weinan Zhang, and Ting Liu. 2017. Chinese zero pronoun resolution with deep memory network. In Proceedings of the EMNLP. Association for Computational Linguistics, 1309--1318.Google Scholar
Cross Ref
- Shanheng Zhao and Hwee Tou Ng. 2007. Identification and resolution of Chinese zero pronouns: A machine learning approach. In Proceedings of the EMNLP-CoNLL. Association for Computational Linguistics, 541--550.Google Scholar
Index Terms
Chinese Zero Pronoun Resolution: A Chain-to-chain Approach
Recommendations
Chinese Zero Pronoun Resolution: A Collaborative Filtering-based Approach
Semantic information that has been proven to be necessary to the resolution of common noun phrases is typically ignored by most existing Chinese zero pronoun resolvers. This is because that zero pronouns convey no descriptive information, which makes it ...
Chinese overt pronoun resolution: a bilingual approach
AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Artificial IntelligenceMuch research has been done on the problem of English pronoun resolution, but there has been relatively little work on the corresponding problem of Chinese pronoun resolution. While pronoun resolution in both languages remains a challenging task, ...
Chinese zero pronoun resolution: an unsupervised approach combining ranking and integer linear programming
AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Artificial IntelligenceState-of-the-art approaches to Chinese zero pronoun resolution are supervised, requiring training documents with manually resolved zero pronouns. To eliminate the reliance on annotated data, we propose an unsupervised approach to this task. Underlying ...






Comments