Elamur ResearchβŒ•
☰
home / papers / 2011 / Coreference Resolution with World Knowledge

Coreference Resolution with World Knowledge

Summary

Earlier work showed that world knowledge helps learning-based coreference resolution. However, those gains were mostly measured on a weak setup: the mention-pair model with Soon et al.'s 12 features. Each knowledge source was also tested alone. Rahman and Ng ask whether the benefits hold with a stronger baseline and whether different sources complement each other. They turn knowledge into features from four kinds of source:

  • YAGO and FrameNet, encyclopedic resources rarely used for this task
  • coreference-annotated data (Noun Pairs, Verb Pairs)
  • unannotated text (Appositives)

These features are added to a 39-feature Baseline. Two models are compared, both trained with SVM light: the classic mention-pair (MP) model and the authors' cluster-ranking (CR) model. Evaluation covers 410 English newswire documents annotated under both the ACE and OntoNotes schemes, scored with B3 and CEAF. Every feature type helps on its own, with YAGO TYPE and Noun Pairs giving the largest gains. Combining the types works best, especially with CR. The study shows that small, noisy knowledge signals add up and that a stronger model exploits them more effectively.

Key points

  • Data: 410 English newswire articles shared by OntoNotes-2 and ACE 2004/2005, split 80/20. OntoNotes yields 4500 coreference chains, while ACE yields 3637.
  • Baseline F-scores for MP were 62.4 B3 and 60.0 CEAF on ACE, and 53.3 and 51.5 on OntoNotes. For CR they were 66.1 and 63.8 on ACE, and 56.2 and 54.0 on OntoNotes.
  • Used alone, the best feature types (YAGO TYPE, Noun Pairs) raise F-measure by 1–2.8 points with MP and by 1.7–2.6 points with CR.
  • The best combined system uses every feature type except Appositives. It beats the Baseline by 3.1–3.3 F points with MP and by 4.1–4.8 points with CR, with both recall and precision rising.
  • Error analysis shows that YAGO and FrameNet can introduce spurious links. Examples include linking "The President" to Nixon, and "The tumor" to colon cancer through related frames.

Our summary of the paper, in our own words β€” not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Coreference resolution

Cited by

42 papers of our library cite it (of the 140673 whose bibliographies we read); 17 of them have a page here, 25 not yet.

Cite

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

@inproceedings{rahman2011coreference,
  title = {{Coreference Resolution with World Knowledge}},
  author = {Rahman, Altaf and Ng, Vincent},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  year = {2011},
  url = {https://aclanthology.org/P11-1082/}
}

References

30 references, 15 of them with a card of ours. β†— leads to the work, Β«findΒ» searches for one we have no id for yet.

  1. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the Linguistic Coreference Workshop at The First International Conference on Language Resources and Evaluation, pages 563–566. find our card
  2. Collin F. Baker, Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics, Volume 1, pages 86–90. find our card
  3. David Bean and Ellen Riloff. 2004. Unsupervised learning of contextual role knowledge for coreference resolution. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 297–304. find our card
  4. Eric Bengtson and Dan Roth. 2008. Understanding the values of features for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 294–303. find
  5. Volha Bryl, Claudio Giuliano, Luciano Serafini, and Kateryna Tymoshenko. 2010. Using background knowledge to support coreference resolution. In Proceedings of the 19th European Conference on Artificial Intelligence, pages 759–764. find
  6. Eugene Charniak. 1972. Towards a Model of Children’s Story Comphrension. AI-TR 266, Artificial Intelligence Laboratory, Massachusetts Institute of Technology. find
  7. Aron Culotta, Michael Wick, and Andrew McCallum. 2007. First-order probabilistic models for coreference resolution. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 81–88. find our card
  8. Hal Daumé III and Daniel Marcu. 2005. A large-scale exploration of effective global features for a joint entity detection and tracking model. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 97–104. find
  9. Pascal Denis and Jason Baldridge. 2008. Specialized models and ranking for coreference resolution. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 660–669. find our card
  10. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by Gibbs sampling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 363–370. find
  11. Michael Fleischman, Eduard Hovy, and Abdessamad Echihabi. 2003. Offline strategies for online question answering: Answering questions before they are asked. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 1–7. find
  12. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 1152–1161. find our card
  13. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: The 90% solution. In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, pages 57–60. find
  14. Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 133–142. find
  15. Xiaoqiang Luo, 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, pages 135–142. find our card
  16. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pages 25– 32. find our card
  17. Ruslan Mitkov. 2002. Anaphora Resolution. Longman. find
  18. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 104–111. find our card
  19. Vincent Ng. 2007. Shallow semantics for coreference resolution. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, pages 1689–1694. find
  20. Simone Paolo Ponzetto and Massimo Poesio. 2009. State-of-the-art NLP approaches to coreference resolution: Theory and practical recipes. In Tutorial Abstracts of ACL-IJCNLP 2009, page 6. find
  21. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 192–199. find our card
  22. Sameer S. Pradhan, Wayne H. Ward, Kadri Hacioglu, James H. Martin, and Dan Jurafsky. 2004. Shallow semantic parsing using support vector machines. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pages 233–240. find
  23. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 968–977. find our card
  24. 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
  25. Veselin Stoyanov, Nathan Gilbert, Claire Cardie, and Ellen Riloff. 2009. Conundrums in noun phrase coreference resolution: Making sense of the state-of-the-art. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language… find our card
  26. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Coreference resolution with Reconcile. In Proceedings of the ACL 2010 Conference Short Papers, pages 156– 161. find our card
  27. Fabian Suchanek, Gjergji Kasneci, and Gerhard Weikum. 2007. YAGO: A core of semantic knowledge unifying wordnet and wikipedia. In Proceedings of the World Wide Web Conference, pages 697–706. find
  28. Olga Uryupina, Massimo Poesio, Claudio Giuliano, and Kateryna Tymoshenko. 2011. Disambiguation and filtering methods in using web knowledge for coreference resolution. In Proceedings of the 24th International Florida Artificial Intelligence Research Society Conference. find
  29. Xiaofeng Yang, Guodong Zhou, Jian Su, and Chew Lim Tan. 2003. Coreference resolution using competitive learning approach. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 176–183. find
  30. Xiaofeng Yang, Jian Su, Jun Lang, Chew Lim Tan, and Sheng Li. 2008. An entity-mention model for coreference resolution with inductive logic programming. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 843–851. find our card

↑ back to top

This page in Markdown β†’ https://md.research.elamur.ai/free/papers/rahman-2011-coreference-resolution-world-knowledge/