Elamur Research⌕
☰
home / papers / 2015 / Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers

Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers

Summary

Chinese often leaves an argument unexpressed: a zero pronoun (ZP) is a silent slot that may refer back to an earlier mention. Because ZPs carry no number or gender cues, they are harder to resolve than overt pronouns. The authors' earlier unsupervised resolver (CN14) learned from overt pronouns and used a pipeline in which heuristic rules first selected anaphoric ZPs. This paper replaces it with a generative probabilistic model trained with EM directly on unannotated ZPs. Each ZP gets a dummy candidate antecedent. Linking a ZP to the dummy marks it as non-anaphoric, so the model detects and resolves anaphoric zero pronouns (AZPs) in one joint step. A discourse salience feature is added, computed from coreference chains built by a rule-based resolver. On the Chinese part of OntoNotes 5.0 (CoNLL-2012), the model beats CN14 in all three evaluation settings. This shows that unsupervised ZP resolution can reach state-of-the-art quality, which matters for languages that lack ZP-annotated data.

Key points

  • Data: Chinese OntoNotes 5.0 from the CoNLL-2012 shared task. Training used 1,391 documents (about 756K words). The official test set has no ZP annotations, so evaluation used the development set (172 documents, 1,713 AZPs) across six sources: NW, MZ, WB, BN, BC and TC.
  • Method: a naive-Bayes-style context model with EM training and Laplace smoothing (θ=1). At test time, ZPs are resolved incrementally from left to right, and NPs filled into earlier gaps become extra candidate antecedents.
  • Salience: computed with SinoCoreferencer. Mentions are weighted by grammatical role (subject 4, object 2, other 1) and decay by 0.5 per sentence of distance, with ranks capped at 5. The dummy entity is ranked top when a ZP shows cues of non-anaphoricity.
  • Results (overall F-score, CN14 → this model):
    • gold parses with gold AZPs: 47.7 → 50.2
    • gold parses with system AZPs: 26.4 → 30.3
    • fully end-to-end: 15.7 → 17.3
  • All gains are statistically significant (paired t-test, p < 0.05).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Discourse analysis · Coreference resolution

Cited by

9 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 4 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/p15-2053

@inproceedings{chen2015chinese,
  title = {{Chinese Zero Pronoun Resolution: A Joint Unsupervised Discourse-Aware Model Rivaling State-of-the-Art Resolvers}},
  author = {Chen, Chen and Ng, Vincent},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-2053},
  url = {https://doi.org/10.3115/v1/p15-2053}
}

References

25 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Eugene Charniak and Micha Elsner. 2009. EM works for pronoun anaphora resolution. In Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics, pages 148--156. find our card
  2. Chen Chen and Vincent Ng. 2013. Chinese zero pronoun resolution: Some recent advances. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1360--1365. find our card
  3. Chen Chen and Vincent Ng. 2014. Chinese zero pronoun resolution: An unsupervised probabilistic model rivaling supervised resolvers. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 763--774. find our card
  4. Colin Cherry and Shane Bergsma. 2005. An expectation maximization approach to pronoun resolution. In Proceedings of the Ninth Conference on Natural Language Learning, pages 88--95. find our card
  5. Susan Converse. 2006. Pronominal Anaphora Resolution in Chinese. Ph.D. thesis, University of Pennsylvania. find
  6. Arthur P. Dempster, Nan M. Laird, and Donald B. Rubin. 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B (Methodological), 39:1--38. find
  7. Antonio Ferrández and Jesús Peral. 2000. A computational approach to zero-pronouns in Spanish. In Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, pages 166--172. find
  8. Barbara J. Grosz, Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203--226. find our card
  9. Na-Rae Han. 2006. Korean zero pronouns: analysis and resolution. Ph.D. thesis, University of Pennsylvania. find
  10. Jerry Hobbs. 1978. Resolving pronoun references. Lingua, 44:311--338. find our card
  11. Ryu Iida and Massimo Poesio. 2011. A cross-lingual ILP solution to zero anaphora resolution. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1, pages 804--813. find our card
  12. Ryu Iida, Kentaro Inui, Hiroya Takamura, and Yuji Matsumoto. 2003. Incorporating contextual cues in trainable models for coreference resolution. In Proceedings of the EACL Workshop on The Computational Treatment of Anaphora, pages 23--30. find
  13. Ryu Iida, Kentaro Inui, and Yuji Matsumoto. 2006. Ex-ploting syntactic patterns as clues in zero-anaphora resolution. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, pages 625--632. find
  14. Ryu Iida, Kentaro Inui, and Yuji Matsumoto. 2007. Zero-anaphora resolution by learning rich syntactic pattern features. ACM Transactions on Asian Language Information Processing, 6(4). find
  15. Kenji Imamura, Kuniko Saito, and Tomoko Izumi. 2009. Discriminative approach to predicate-argument structure analysis with zero-anaphora resolution. In Proceedings of the ACL-IJCNLP 2009 Conference Short Papers, pages 85--88. find our card
  16. Hideki Isozaki and Tsutomu Hirao. 2003. Japanese zero pronoun resolution based on ranking rules and machine learning. In Proceedings of the 2003 Conference on Empirical methods in natural language processing, pages 184--191. find our card
  17. Fang Kong and Hwee Tou Ng. 2013. Exploiting zero pronouns to improve chinese coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 278--288. find our card
  18. Fang Kong and Guodong Zhou. 2010. A tree kernel-based unified framework for Chinese zero anaphora resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 882--891. find our card
  19. Shalom Lappin and Herbert Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535--562. find our card
  20. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Proceedings of 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Languag… find our card
  21. Ryohei Sasano and Sadao Kurohashi. 2011. A discriminative approach to Japanese zero anaphora resolution with large-scale lexicalized case frames. In Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 758-- 766. find our card
  22. Kazuhiro Seki, Atsushi Fujii, and Tetsuya Ishikawa. 2002. A probabilistic method for analyzing Japanese anaphora integrating zero pronoun detection and resolution. In Proceedings of the 19th International Conference on Computational linguistics. find our card
  23. Ching-Long Yeh and Yi-Chun Chen. 2007. Zero anaphora resolution in Chinese with shallow parsing. Journal of Chinese Language and Computing, 17(1):41--56. find
  24. Shanheng Zhao and Hwee Tou Ng. 2007. Identification and resolution of Chinese zero pronouns: A machine learning approach. In Proceedings of the 2007 Joint Conference on Empirical Methods on Natural Language Processing and Computational Natural Language Learning, pages 541--550. find our card
  25. GuoDong Zhou, Fang Kong, and Qiaoming Zhu. 2008. Context-sensitive convolution tree kernel for pronoun resolution. In Proceedings of the 3rd International Joint Conference on Natural Language Processing, pages 25--31. find our card

↑ back to top