Elamur Research⌕
☰
home / papers / 2011 / A Cross-Lingual ILP Solution to Zero Anaphora Resolution

A Cross-Lingual ILP Solution to Zero Anaphora Resolution

Summary

Iida and Poesio address zero anaphora in pro-drop languages, where a verb's subject is omitted but still refers to an entity in the discourse. A resolver must decide both whether a subject is missing and which mention it refers to. The authors treat these two decisions as one joint optimisation problem using Integer Linear Programming (ILP). They start from the Denis and Baldridge (2007) model, which jointly infers anaphoricity and coreference, and make two changes:

  • a stricter "Best First" constraint, so that each zero receives at most one antecedent;
  • a third classifier for subject detection, tied to the others by a constraint that a verb cannot have both an overt subject and a zero subject.

They test the model on Italian (Wikipedia articles from the SemEval 2010 coreference data) and Japanese (NAIST Text Corpus). It beats baselines and a direct port of Denis and Baldridge for both languages. Plugged into a full coreference resolver, it also improves overall results, but only when zeros and overt anaphors are handled by separate classifiers. This matters because SemEval 2010 systems performed poorly on zeros.

Key points

  • The ILP objective combines three classifiers: antecedent identification (pairwise), anaphoricity/zero detection, and subject detection based on parser output. Only subject zeros are modelled.
  • Italian data: 97 training and 46 test documents. Preprocessing used TextPro, parsing used DESR, and system mentions came from I-BART.
  • Japanese data: NAIST Text Corpus 1.4β (1,753 training and 696 test documents), plus the Kyoto University Text Corpus, CaboCha and Chasen. About 64.3% of anaphors in NAIST are zeros.
  • Italian overall coreference (MUC): ILP + BF + SUBJ with separate classifiers reached F = 0.547 with gold mentions, compared with 0.482 for I-BART. With system mentions it reached 0.446, compared with 0.308.
  • Remaining weakness and future work: precision is still low, mainly because of generic-"they"-like zeros. Proposed next steps are detecting such generic uses, using stronger antecedent models, and adding mention detection to the ILP.

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

39 papers of our library cite it (of the 140673 whose bibliographies we read); 16 of them have a page here, 23 not yet.

Cite

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

@inproceedings{iida2011cross,
  title = {{A Cross-Lingual ILP Solution to Zero Anaphora Resolution}},
  author = {Iida, Ryu and Poesio, Massimo},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  year = {2011},
  url = {https://aclanthology.org/P11-1081/}
}

References

26 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. G. Attardi, F. Dell’Orletta, M. Simi, A. Chanev, and M. Ciaramita. 2007. Multilingual dependency parsing and domain adaptation using desr. In Proc. of the CoNLL Shared Task Session of EMNLP-CoNLL 2007, Prague. find
  2. C. Bosco, S. Montemagni, A. Mazzei, V. Lombardo, F. Dell’Orletta, A. Lenci, L. Lesmo, G. Attardi, M. Simi, A. Lavelli, J. Hall, J. Nilsson, and J. Nivre. 2010. Comparing the influence of different treebank annotations on dependency parsing. In Proceedings of LREC, pages 1794–1801. find
  3. P. Denis and J. Baldridge. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In Proc. of HLT/NAACL, pages 236– 243. find our card
  4. B. Di Eugenio. 1998. Centering in Italian. In M. A. Walker, A. K. Joshi, and E. F. Prince, editors, Centering Theory in Discourse, chapter 7, pages 115–138. Oxford. find
  5. B. J. Grosz, A. K. Joshi, and S. Weinstein. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21(2):203–226. find our card
  6. R. Iida, K. Inui, H. Takamura, and Y. Matsumoto. 2003. Incorporating contextual cues in trainable models for coreference resolution. In Proceedings of the 10th EACL Workshop on The Computational Treatment of Anaphora, pages 23–30. find
  7. R. Iida, K. Inui, and Y. Matsumoto. 2007a. Zero-anaphora resolution by learning rich syntactic pattern features. ACM Transactions on Asian Language Information Processing (TALIP), 6(4). find
  8. R. Iida, M. Komachi, K. Inui, and Y. Matsumoto. 2007b. Annotating a Japanese text corpus with predicate-argument and coreference relations. In Proceeding of the ACL Workshop ‘Linguistic Annotation Workshop’, pages 132–139. find our card
  9. K. Imamura, K. Saito, and T. Izumi. 2009. Discriminative approach to predicate-argument structure analysis with zero-anaphora resolution. In Proceedings of ACL-IJCNLP, Short Papers, pages 85–88. find our card
  10. H. Isozaki and T. Hirao. 2003. Japanese zero pronoun resolution based on ranking rules and machine learning. In Proceedings of EMNLP, pages 184–191. find our card
  11. M. Kameyama. 1985. Zero Anaphora: The case of Japanese. Ph.D. thesis, Stanford University. find
  12. H. Kobdani and H. Schütze. 2010. Sucre: A modular system for coreference resolution. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 92–95. find our card
  13. T. Kudo and Y. Matsumoto. 2004. A boosting algorithm for classification of semi-structured text. In Proceedings of EMNLP, pages 301–308. find
  14. V. Ng and C. Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th ACL, pages 104–111. find our card
  15. E. Pianta, C. Girardi, and R. Zanoli. 2008. The TextPro tool suite. In In Proceedings of LREC, pages 28–30. find
  16. M. Poesio, O. Uryupina, and Y. Versley. 2010. Creating a coreference resolution system for Italian. In Proceedings of LREC. find our card
  17. M. Recasens, L. Màrquez, E. Sapena, M. A. Martı́, M. Taulé, V. Hoste, M. Poesio, and Y. Versley. 2010. Semeval-2010 task 1: Coreference resolution in multiple languages. In Proceedings of the 5th International Workshop on Semantic Evaluation, pages 1–8. find our card
  18. K-J. Rodriguez, F. Delogu, Y. Versley, E. Stemle, and M. Poesio. 2010. Anaphoric annotation of wikipedia and blogs in the live memories corpus. In Proc. LREC. find our card
  19. D. Roth and W.-T. Yih. 2004. A linear programming formulation for global inference in natural language tasks. In Proc. of CONLL. find our card
  20. R. Sasano, D. Kawahara, and S. Kurohashi. 2009. The effect of corpus size on case frame acquisition for discourse analysis. In Proceedings of HLT/NAACL, pages 521–529. find
  21. K. Seki, A. Fujii, and T. Ishikawa. 2002. A probabilistic method for analyzing Japanese anaphora integrating zero pronoun detection and resolution. In Proceedings of the 19th COLING, pages 911–917. find our card
  22. W. M. Soon, H. T. Ng, and D. C. Y. Lim. 2001. A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521– 544. find our card
  23. H. Taira, S. Fujita, and M. Nagata. 2008. A Japanese predicate argument structure analysis using decision lists. In Proceedings of EMNLP, pages 523–532. find
  24. H. Taira, S. Fujita, and M. Nagata. 2010. Predicate argument structure analysis using transformation based learning. In Proceedings of the ACL 2010 Conference Short Papers, pages 162–167. find
  25. M. A. Walker, M. Iida, and S. Cote. 1994. Japanese discourse and the process of centering. Computational Linguistics, 20(2):193–232. find
  26. X. Yang, J. Su, and C. L. Tan. 2008. Twin-candidate model for learning-based anaphora resolution. Computational Linguistics, 34(3):327–356. find

↑ back to top