Elamur Research⌕
☰
home / papers / 2014 / Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers

Summary

The paper addresses anaphoric zero pronoun (AZP) resolution in Chinese, which means linking an omitted subject to an earlier noun phrase. Previous strong systems depended on supervised training with manually resolved zero pronouns. Chen and Ng propose an unsupervised generative model built on one idea: a resolver trained without labels on overt pronouns can be transferred to zero pronouns. Using EM, the model learns two things from raw text. The first is how ten Chinese personal pronouns relate to candidate antecedents through Number, Gender, Person and Animacy. The second is how contextual features predict coreference. At test time, AZPs are handled left to right, and each resolved gap is filled with its chosen antecedent so that later, more distant zero pronouns can draw on it. On the Chinese portion of OntoNotes 5.0 with gold AZPs, the model matches the best supervised resolver. The authors also introduce a rule-based AZP identifier for end-to-end evaluation. This matters because the generative process is not language-specific, so the approach could serve languages that lack annotated zero-pronoun data.

Key points

  • The model is trained only on overt pronouns that are surface or deep subjects, because 99.56% of zero pronouns in OntoNotes 5.0 occupy subject positions. Candidate antecedents are maximal or modifier NPs no more than two sentences back.
  • With gold AZPs (Setting 1), the model reaches an F-score of 47.7 (R 47.5, P 47.9), equal to the supervised state of the art (Chen and Ng, 2013). In the hardest setting (Setting 3), F falls to 15.7.
  • Removing the context features costs 14.7 F points in Setting 1. The rule-based context feature (feature 8) is the most valuable single feature, at −6.4 F. Dropping Number changes nothing, since nearly all candidates are singular.
  • An analysis of 100 errors identifies three main causes:
    • missed document topics (32 errors);
    • weak semantic-compatibility modeling based only on mutual information with the governing verb (28 errors);
    • failure to exploit semantically parallel sentences (23 errors).

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: Coreference resolution

Cited by

6 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 1 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/d14-1084

@inproceedings{chen2014chinese,
  title = {{Chinese Zero Pronoun Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers}},
  author = {Chen, Chen and Ng, Vincent},
  booktitle = {Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2014},
  doi = {10.3115/v1/d14-1084},
  url = {https://doi.org/10.3115/v1/d14-1084}
}

References

27 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Shane Bergsma and Dekang Lin. 2006. Bootstrapping path-based pronoun resolution. In Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, pages 33--40. find our card
  2. 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
  3. 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
  4. Chen Chen and Vincent Ng. 2014. SinoCoreferencer: An end-to-end Chinese event coreference resolver. In Proceedings of the 9th International Conference on Language Resources and Evaluation, pages 4532--4538. find our card
  5. 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
  6. Susan Converse. 2006. Pronominal Anaphora Resolution in Chinese. Ph.D. thesis, University of Pennsylvania. find
  7. 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
  8. 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
  9. 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
  10. Na-Rae Han. 2006. Korean Zero Pronouns: Analysis and Resolution. Ph.D. thesis, University of Pennsylvania. find
  11. Jerry Hobbs. 1978. Resolving pronoun references. Lingua, 44:311--338. find our card
  12. 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, pages 804--813. find our card
  13. Ryu Iida, Kentaro Inui, and Yuji Matsumoto. 2006. Exploiting 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 our card
  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. Andrew Kehler, Douglas Appelt, Lara Taylor, and Aleksandr Simma. 2004. The (non)utility of predicate-argument frequencies for pronoun interpretation. In Proceedings of 2004 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 289-… find
  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. Robert Parker, David Graff, Ke Chen, Junbo Kong, and Kazuaki Maeda. 2009. Chinese Gigaword fourth edition. Linguistic Data Consortium. Philadelphia, PA. find
  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. Xian Qian, Qi Zhang, Xuangjing Huang, and Lide Wu. 2010. 2d trie for fast parsing. In Proceedings of the 23rd International Conference on Computational Linguistics, pages 904--912. find
  22. 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
  23. 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
  24. Xiaofeng Yang, Jian Su, and Chew Lim Tan. 2005. Improving pronoun resolution using statistics-based semantic compatibility information. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 165--172. find our card
  25. 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
  26. 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
  27. 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