Elamur Research⌕
☰
home / papers / 2006 / Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution

Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution

Summary

Japanese often omits even obligatory predicate arguments. In the authors' newspaper corpus, verbs leave their nominative argument unexpressed 45.5% of the time, so recovering the referents of these missing arguments (zero-anaphora resolution) is important for many NLP applications. Iida, Inui and Matsumoto argue that anaphora resolution (AR) and semantic role labeling (SRL) research have developed separately and could borrow from each other. They split the task into intra-sentential and inter-sentential cases and build a separate component for each, based on the selection-then-classification model (SCM). In each component, a tournament model picks the best candidate antecedent through pairwise comparisons. An anaphoricity classifier then accepts or rejects that candidate against a threshold. The intra-sentential component also receives SRL-style syntactic pattern features that describe the parse-tree path between a zero-pronoun and a candidate antecedent. Experiments on Japanese show that these features greatly improve intra-sentential accuracy. This gain carries over to better overall resolution compared with an SVM-trained SCM baseline that handles both cases jointly without syntactic patterns. The work connects AR and SRL methods and is relevant to languages with frequent argument dropping.

Key points

  • The model runs as a cascade:
    • An intra-sentential tournament model selects a candidate, which is accepted if its score passes θ_intra.
    • Otherwise, an inter-sentential tournament model selects a candidate, which is accepted if it passes θ_inter.
    • If neither threshold is met, the zero-pronoun is labeled non-anaphoric.
  • Only zero-pronouns filling obligatory argument slots are handled. These can be non-anaphoric, for example when they refer to an unmentioned first or second person.
  • Error analysis split the test cases into 262 zero-pronouns inside quotations and 733 outside them. Accuracy on in-quote cases was much lower, which suggests they need a dedicated model that accounts for nested discourse.
  • Recall-precision curves show the proposed model clearly beats the original SCM when θ_intra is set appropriately. The AUC is fairly flat across θ_intra values, so the threshold is easy to tune.
  • Planned future work includes detecting zero-pronouns jointly with predicate-argument structure analysis and finding globally optimal solutions across a whole discourse.

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 · Semantic role labeling

Cited by

28 papers of our library cite it (of the 140673 whose bibliographies we read); 14 of them have a page here, 14 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/1220175.1220254

@inproceedings{iida2006exploiting,
  title = {{Exploiting Syntactic Patterns as Clues in Zero-Anaphora Resolution}},
  author = {Iida, Ryu and Inui, Kentaro and Matsumoto, Yuji},
  booktitle = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics},
  year = {2006},
  doi = {10.3115/1220175.1220254},
  url = {https://doi.org/10.3115/1220175.1220254}
}

References

28 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. M. Asahara and Y. Matsumoto, 2003. IPADIC User Manual. Nara Institute of Science and Technology, Japan. find
  2. B. Baldwin. 1995. CogNIAC: A Discourse Processing Engine. Ph.D. thesis, Department of Computer and Information Sciences, University of Pennsylvania. find
  3. X. Carreras and L. Marquez. 2005. Introduction to the conll-2005 shared task: Semantic role labeling. In Proceedings of the Ninth CoNll, pages 152–164. find our card
  4. M. Collins and N.l Duffy. 2001. Convolution kernels for natural language. In Proceedings of the NIPS, pages 625– 632. find
  5. A. Fujita, K. Inui, and Y. Matsumoto. 2004. Detection of incorrect case assignments in automatically generated paraphrases of japanese sentences. In Proceeding of the first IJCNLP, pages 14–21. find
  6. D. Gildea and D. Jurafsky. 2002. Automatic labeling of semantic roles. In Computational Linguistics, pages 245– 288. find our card
  7. 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
  8. 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
  9. R. Iida, K. Inui, and Y. Matsumoto. 2005. Anaphora resolution by antecedent identification followed by anaphoricity determination. ACM Transactions on Asian Language Information Processing (TALIP), 4:417–434. find
  10. S. Ikehara, M. Miyazaki, S. Shirai A. Yokoo, H. Nakaiwa, K. Ogura, Y. Ooyama, and Y. Hayashi. 1997. Nihongo Goi Taikei (in Japanese). Iwanami Shoten. find
  11. Japan Electronic Dictionary Research Institute, Ltd. Japan, 1995. EDR Electronic Dictionary Technical Guide. find
  12. M. Kameyama. 1986. A property-sharing constraint in centering. In Proceedings of the 24th ACL, pages 200–206. find
  13. T. Kudo and Y. Matsumoto. 2004. A boosting algorithm for classification of semi-structured text. In Proceedings of the 2004 EMNLP, pages 301–308. find
  14. S. Lappin and H. J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):535–561. find our card
  15. A. McCallum and B. Wellner. 2003. Object consolidation by graph partitioning with a conditionally trained distance metric. In Proceedings of the KDD-2003 Workshop on Data Cleaning, Record Linkage, and Object Consolidation, pages 19–24. find
  16. J. F. McCarthy and W. G. Lehnert. 1995. Using decision trees for coreference resolution. In Proceedings of the 14th IJCAI, pages 1050–1055. find
  17. R. Mitkov. 1997. Factors in anaphora resolution: they are not the only things that matter. a case study based on two different approaches. In Proceedings of the ACL’97/EACL’97 Workshop on Operational Factors in Practical, Robust Anaphora Resolution. find our card
  18. H. Nakaiwa and S. Shirai. 1996. Anaphora resolution of japanese zero pronouns with deictic reference. In Proceedings of the 16th COLING, pages 812–817. find our card
  19. V. Ng. 2004. Learning noun phrase anaphoricity to improve coreference resolution: Issues in representation and optimization. In Proceedings of the 42nd ACL, pages 152– 159. find
  20. V. Ng and C. Cardie. 2002a. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th ACL, pages 104–111. find our card
  21. M. Okumura and K. Tamura. 1996. Zero pronoun resolution in japanese discourse based on centering theory. In Proceedings of the 16th COLING, pages 871–876. find our card
  22. M. Poesio, O. Uryupina, R. Vieira, M. Alexandrov-Kabadjov, and R. Goulart. 2004. Discourse-new detectors for definite description resolution: A survey and a preliminary proposal. In Proceedings of the 42nd ACL Workshop on Reference Resolution and its Applications, pages 47–54. find
  23. 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
  24. 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
  25. M. Strube and C. Müller. 2003. A machine learning approach to pronoun resolution in spoken dialogue. In Proceedings of the 41st ACL, pages 168–175. find our card
  26. J. Suzuki, T. Hirao, Y. Sasaki, and E. Maeda. 2003. Hierarchical directed acyclic graph kernel: Methods for structured natural language data. In Proceeding of the 41st ACL, pages 32–39. find
  27. V. N. Vapnik. 1998. Statistical Learning Theory. Adaptive and Learning Systems for Signal Processing Communications, and control. John Wiley & Sons. find
  28. X. Yang, G. Zhou, J. Su, and C. L. Tan. 2003. Coreference resolution using competition learning approach. In Proceedings of the 41st ACL, pages 176–183. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/iida-2006-exploiting-syntactic-patterns-as-clues/