Elamur Research⌕
☰
home / papers / 2008 / A Twin-Candidate Model for Learning-Based Anaphora Resolution

A Twin-Candidate Model for Learning-Based Anaphora Resolution

Summary

The paper addresses a weakness of the standard single-candidate approach to learning-based anaphora resolution. That approach judges each potential antecedent independently, so it cannot learn which of several competing candidates should be preferred. The authors propose a twin-candidate model that treats resolution as preference classification. Each instance pairs an anaphor with two candidates, and a classifier decides which candidate is better. The final antecedent comes from ranking candidates through these pairwise judgments, using either an Elimination or a Round Robin scheme. The model works with any discriminative learner. The authors also adapt it to full coreference resolution, where some NPs have no antecedent. They test it on the Automatic Content Extraction (ACE) data in three domains with C5, MaxEnt and SVM learners. For pronoun resolution, the twin-candidate model is significantly more accurate than the single-candidate baseline. For non-pronoun and overall coreference, it matches or beats the baseline. This shows that explicitly modelling competition between candidates improves mention-level resolution.

Key points

  • Evaluation uses the ACE data sets across the NWire, NPaper and BNews domains, with C5, MaxEnt and SVM classifiers. Coreference is scored with Vilain et al.'s (1995) algorithm.
  • For pronominal anaphora, the twin-candidate model improves average accuracy over the single-candidate baseline by up to 4.2%, and the gains are statistically significant.
  • In full coreference with MaxEnt, F-measure rises from 58.3/61.5/62.2 (single-candidate) to 59.2/63.3/63.0 (twin-candidate, Round Robin) for NWire/NPaper/BNews.
  • Earlier pairwise work reported much weaker or hard-to-compare results:
    • Connolly et al. (1997): 55.3% for pronouns and 37.4% for definite NPs.
    • Iida et al. (2003), "tournament model" for Japanese zero anaphora: about 70%.
  • Proposed future work includes richer features, such as statistics-based semantic compatibility, and instance sampling to filter out low-confidence candidates and uninformative non-anaphors.

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

16 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli.2008.07-004-r2-06-57

@article{yang2008twin,
  title = {{A Twin-Candidate Model for Learning-Based Anaphora Resolution}},
  author = {Yang, Xiaofeng and Su, Jian and Tan, Chew Lim},
  journal = {Computational Linguistics},
  year = {2008},
  doi = {10.1162/coli.2008.07-004-r2-06-57},
  url = {https://doi.org/10.1162/coli.2008.07-004-r2-06-57}
}

References

38 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Aone, Ghinatsu and Scott W. Bennett. 1995. Evaluating automated and manual acquisition of anaphora resolution strategies. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 122–129, Cambridge, Massachusetts. find our card
  2. Berger, Adam L., Stephen A. Della Pietra, and Vincent J. Della Pietra. 1996. A maximum entropy approach to natural language processing. Computational Linguistics, 22(1):39–71. find our card
  3. Chomsky, Noam. 1981. Lectures on Government and Binding. Foris, Dordrecht, The Netherlands. find
  4. Clark, Herber H. and C. J. Sengul. 1979. In search of referents for noun phrases and pronouns. Memory and Cognition, 7:35–41. find
  5. Connolly, Dennis, John D. Burger, and David S. Day, 1997. A machine learning approach to anaphoric reference. In New Methods in Language Processing, pages 133–144, Taylor and Francis, Bristol, Pennsylvania. find
  6. Crawley, Rosalind A., Rosemary J. Stevenson, and David Kleinman. 1990. The use of heuristic strategies in the interpretation of pronouns. Journal of Psycholinguistic Research, 19:245–264. find
  7. Denis, Pascal and Jason Baldridge. 2007. A ranking approach to pronoun resolution. In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), pages 1588–1593, Hyderabad, India. find
  8. Garnham, Alan, 2001. Mental Models and the Interpretation of Anaphora. Psychology Press Ltd., Hove, East Sussex, UK. find
  9. Ge, Niyu, John Hale, and Eugene Charniak. 1998. A statistical approach to anaphora resolution. In Proceedings of the 6th Workshop on Very Large Corpora, pages 161–171, Montreal, Quebec, Canada. find our card
  10. Gernsbacher, Morton A. and David Hargreaves. 1988. Accessing sentence participants: The advantage of first mention. Journal of Memory and Language, 27:699–717. find
  11. Grober, Ellen H., William Beardsley, and Alfonso Caramazza. 1978. Parallel function in pronoun assignment. Cognition, 6:117–133. find
  12. Grosz, Barbara J., 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
  13. Hobbs, Jerry. 1978. Resolving pronoun references. Lingua, 44:339–352. find our card
  14. Iida, Ryu, Kentaro Inui, Hiroya Takamura, and Yuji Matsumoto. 2003. Incorporating contextual cues in trainable models for coreference resolution. In Proceedings of the 10th Conference of EACL, Workshop ”The Computational Treatment of Anaphora,” pages 23–30, Budapest, Hungary. find
  15. Joachims, Thorsten. 2002. Optimizing search engines using clickthrough data. In Proceedings of the ACM Conference on Knowledge Discovery and Data Mining (KDD), pages 133–142, Edmonton, Alberta, Canada. find
  16. Jurafsky, Daniel and James H. Martin. 2000. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. Prentice Hall, Upper Saddle River, New Jersey. find
  17. Kehler, Andrew. 1997. Probabilistic coreference in information extraction. In Proceedings of the 2nd Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 163–173, Providence, Rhode Island. find our card
  18. Kehler, Andrew, Douglas Appelt, Lara Taylor, and Aleksandr Simma. 2004. The (non)utility of predicate-argument frequencies for pronoun interpretation. In Proceedings of the North American Chapter of the Association for Computational Linguistics annual meeting (NAACL), pages 289–296, Boston, MA. find
  19. Lappin, Shalom and Herbert J. Leass. 1994. An algorithm for pronominal anaphora resolution. Computational Linguistics, 20(4):525–561. find our card
  20. Luo, Xiaoqiang, Abe Ittycheriah, Hongyan Jing, Nanda Kambhatla, and Salim Roukos. 2004. A mention-synchronous coreference resolution algorithm based on the bell tree. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL), pages 135–142, Barcelona, Spain. find our card
  21. McCarthy, Joseph F. and Wendy G. Lehnert. 1995. Using decision trees for coreference resolution. In Proceedings of the 14th International Conference on Artificial Intelligences (IJCAI), pages 1050–1055, Montreal, Quebec, Canada. find
  22. McEnery, A., I. Tanaka, and S. Botley. 1997. Corpus annotation and reference resolution. In Proceedings of the ACL Workshop on Operational Factors in Practical Robust Anaphora Resolution for Unrestricted Texts, pages 67–74, Madrid, Spain. find
  23. Ng, Hwee Tou, Yu Zhou, Robert Dale, and Mary Gardiner. 2005. Machine learning approach to identification and resolution of one-anaphora. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI), pages 1105–1110, Edinburgh, Scotland. find
  24. Ng, Vincent. 2005. Machine learning for coreference resolution: From local classification to global ranking. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), pages 157–164, Ann Arbor, Michigan. find our card
  25. Ng, Vincent and Claire Cardie. 2002a. Combining sample selection and error-driven pruning for machine learning of coreference rules. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 55–62, Philadelphia, PA. find our card
  26. Ng, Vincent and Claire Cardie. 2002b. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pages 104–111, Philadelphia, PA. find our card
  27. Preiss, Judita. 2001. Machine learning for anaphora resolution. Technical Report CS-01-10, University of Sheffield, Sheffield, England. find
  28. Quinlan, J. Ross. 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Francisco, CA. find our card
  29. Soon, Wee Meng, 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
  30. Stevenson, Rosemary J., Alexander W. R. Nelson, and Keith Stenning. 1995. The role of parallelism in strategies of pronoun comprehension. Language and Speech, 29:393–418. find
  31. Strube, Michael and Christoph Mueller. 2003. A machine learning approach to pronoun resolution in spoken dialogue. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL), pages 168–175, Sapporo, Japan. find our card
  32. Vapnik, Vladimir N. 1995. The Nature of Statistical Learning Theory. Springer-Verlag, New York, NY. find
  33. Vilain, Marc, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the Sixth Message Understanding Conference (MUC-6), pages 45–52, San Francisco, CA. find our card
  34. Wilks, Yorick. 1973. Preference Semantics. Stanford AI Laboratory Memo AIM-206. Stanford University. find
  35. Winograd, Terry. 1972. Understanding Natural Language. Academic Press, New York. find
  36. Yang, Xiaofeng, 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 (ACL), pages 165–172, Ann Arbor, MI. find our card
  37. Zhou, Guodong and Jian Su. 2000. Error-driven HMM-based chunk tagger with context-dependent lexicon. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, pages 71–79, Hong Kong. find
  38. Zhou, Guodong and Jian Su. 2002. Named Entity recognition using a HMM-based chunk tagger. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), pages 473–480, Philadelphia, PA. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/yang-2008-twin-candidate-model-learning-based/