Elamur Research⌕
☰
home / papers / 2007 / Identification and Resolution of Chinese Zero Pronouns: A Machine Learning Approach

Identification and Resolution of Chinese Zero Pronouns: A Machine Learning Approach

Summary

Chinese often leaves subjects and other arguments unexpressed. These gaps are zero pronouns, and many refer back to an overt noun phrase earlier in the text. This anaphoric type (AZP) is hard to find and resolve because, unlike overt pronouns, it carries no gender or number cues. Earlier Chinese systems relied on hand-crafted rules or assumed the gaps were already given. Zhao and Ng propose the first fully learned pipeline that both detects and resolves AZPs.

The work uses Converse's (2006) coreference annotation of 205 Penn Chinese TreeBank (CTB 3.0) texts, with gold segmentation, POS tags and parse trees (null categories removed). Candidate gaps are taken from positions before VP-initial words. A first classifier decides which gaps are anaphoric. A second classifier pairs each detected AZP with preceding NP candidates. Both rely on simple syntactic, parse-tree-based features, and the anaphoricity threshold is tuned.

The full system reaches an F-measure of 25.9% on blind test data. Given gold AZPs, resolution performs about as well as Converse's rule-based Hobbs-algorithm system, which shows that learning can replace hand-built heuristics for this task.

Key points

  • Data: 205 CTB texts. Texts 1–155 are used for training (343 AZPs) and 156–205 for testing (40 AZPs). Chains with split antecedents were dropped, leaving 383 AZPs in total.
  • Candidate extraction finds 100% of zero pronouns and 98.6% of NPs.
  • After tuning (r = 11 training-sample window, threshold t = 0.6) with 5-fold cross validation, blind test results are 27.5% recall, 24.4% precision and 25.9% F. The tuning gain was modest but statistically significant.
  • With gold AZPs, resolution scores 42.5% F, compared with 43.0% accuracy for Converse's (2006) rule-based approach.
  • Motivation: overt subjects appear in only about 64% of Chinese clauses, versus over 96% in English (Kim, 2000).

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

44 papers of our library cite it (of the 140673 whose bibliographies we read); 18 of them have a page here, 26 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{zhao2007identification,
  title = {{Identification and Resolution of Chinese Zero Pronouns: A Machine Learning Approach}},
  author = {Zhao, Shanheng and Ng, Hwee Tou},
  booktitle = {Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
  year = {2007},
  url = {https://aclanthology.org/D07-1057/}
}

References

19 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Susan Converse. 2006. Pronominal Anaphora Resolution in Chinese. Ph.D. thesis, Department of Computer and Information Science, University of Pennsylvania. find
  2. Antonio Ferrández and Jesús Peral. 2000. A computational approach to zero-pronouns in Spanish. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL2000), pages 166–172. find
  3. Radu Florian, Hany Hassan, Abraham Ittycheriah, Hongyan Jing, Nanda Kambhatla, Xiaoqiang Luo, Nicolas Nicolov, and Salim Roukos. 2004. A statistical model for multilingual entity detection and tracking. In Proceedings of the Human Language Technology Conference and North American Chapter of the Asso… find
  4. Barbara J. Grosz, Aravind K. Joshi, and Scott Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–225. find our card
  5. Jerry R. Hobbs. 1978. Resolving pronoun references. Lingua, 44:311–338. find our card
  6. 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 44th Annual Meeting of the Association for Computational Linguistics (COLING-ACL2006), pages 625–… find our card
  7. Young-Joo Kim. 2000. Subject/object drop in the acquisition of Korean: A cross-linguistic comparison. Journal of East Asian Linguistics, 9(4):325–351. find
  8. Charles N. Li and Sandra A. Thompson. 1979. Third-person pronouns and zero-anaphora in Chinese discourse. Syntax and Semantics, 12:311–335. find
  9. Wendan Li. 2004. Topic chains in Chinese discourse. Discourse Processes, 37(1):25–45. find
  10. Andrew McCallum and Ben Wellner. 2005. Conditional models of identity uncertainty with application to noun coreference. In Advances in Neural Information Processing Systems 17 (NIPS), pages 905–912. find
  11. Vincent Ng and Claire Cardie. 2002a. Identifying anaphoric and non-anaphoric noun phrases to improve coreference resolution. In Proceedings of the 19th International Conference on Computational Linguistics (COLING2002), pages 1–7. find
  12. Vincent Ng and Claire Cardie. 2002b. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL2002), pages 104–111. find our card
  13. Vincent Ng. 2004. Learning noun phrase anaphoricity to improve coreference resolution: Issues in representation and optimization. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL2004), pages 152–159. find
  14. 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 (COLING2002), pages 911–917. find our card
  15. Wee Meng Soon, Hwee Tou Ng, and Daniel Chung Yong Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521–544. find our card
  16. Nianwen Xue, Fei Xia, Fu-Dong Chiou, and Martha Palmer. 2005. The Penn Chinese TreeBank: Phrase structure annotation of a large corpus. Natural Language Engineering, 11(2):207–238. find
  17. Xiaofeng Yang, Guodong Zhou, Jian Su, and Chew Lim Tan. 2003. Coreference resolution using competition learning approach. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL2003), pages 176–183. find our card
  18. Ching-Long Yeh and Yi-Chun Chen. 2004. Zero anaphora resolution in Chinese with shallow parsing. Journal of Chinese Language and Computing. find
  19. Yaqian Zhou, Changning Huang, Jianfeng Gao, and Lide Wu. 2005. Transformation based Chinese entity detection and tracking. In Proceedings of the Second International Joint Conference on Natural Language Processing (IJCNLP 2005), pages 232–237. find

↑ back to top