Elamur Research
☰
home / papers / 2015 / Entity-Centric Coreference Resolution with Model Stacking

Entity-Centric Coreference Resolution with Model Stacking

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/P15-1136.pdf

Summary

Coreference systems that score pairs of mentions are accurate and simple to train, but they ignore what is already known about whole entities. They are usually combined with heuristics such as best-first clustering, which can yield incoherent chains like [Hillary Clinton, Clinton, he]. Clark and Manning bridge pairwise and entity-centric approaches through model stacking. They first train two logistic mention pair models: a classification model and a ranking model. The outputs of these models then serve as cluster-level features for an agent that merges clusters agglomeratively. The agent works in easy-first order and is trained by imitation learning based on DAgger. Rather than relying on heuristic notions of good actions, each merge receives an exact cost derived from coreference evaluation metrics, which captures how severe a mistake is. The pairwise scores also order candidate merges and prune unlikely ones, which makes training tractable. On the English part of the CoNLL 2012 Shared Task, the system reaches a CoNLL average F1 of 63.02 and surpasses earlier state-of-the-art systems. This shows that learned, metric-driven clustering over stacked pairwise scores is effective.

Key points

  • The two mention pair models differ only in their training objective:
    • The classification model is optimized over all candidate antecedents.
    • The ranking model uses log-likelihood over the best true and best false antecedent, which keeps scores comparable across mentions.
    • Both use L1 regularization (λ = 0.001) and are optimized with AdaGrad.
  • Features include distance, syntactic, semantic, lexical and rule-based cues, plus a conjunction scheme following Durrett and Klein (2013).
  • Pairwise scores sort merges in easy-first order, and a threshold discards more than 95% of mention pairs before the agent runs.
  • Test-set results on CoNLL 2012 English:
    • This system: 63.02 CoNLL F1.
    • Durrett & Klein (JOINT): 61.71.
    • Björkelund & Kuhn: 61.63.
    • Ma et al.: 61.56.
    • The system has the best B³ F1 (60.44) and CEAFφ4 F1 (56.02).
  • The learned entity-centric agent clearly beats best-first clustering. Combining both pairwise models improves accuracy, while adding classic entity-level features did not help.

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

93 papers of our library cite it (of the 140673 whose bibliographies we read); 20 of them have a page here, 73 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/p15-1136

@inproceedings{clark2015entity,
  title = {{Entity-Centric Coreference Resolution with Model Stacking}},
  author = {Clark, Kevin and Manning, Christopher D.},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-1136},
  url = {https://doi.org/10.3115/v1/p15-1136}
}

References

41 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5):469–483. find
  2. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In The First International Conference on Language Resources and Evaluation Workshop on Linguistics Coreference, pages 563–566. find our card
  3. David L Bean and Ellen Riloff. 2004. Unsupervised learning of contextual role knowledge for coreference resolution. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 297–304. find
  4. Eric Bengtson and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 294–303. find our card
  5. Anders Björkelund and Richárd Farkas. 2012. Data-driven multilingual coreference resolution using resolver stacking. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning - Shared Task, pages 49–55. find
  6. Anders Björkelund and Jonas Kuhn. 2014. Learning structured perceptrons for coreference resolution with latent antecedents and non-local features. In Association of Computational Linguistics (ACL). find
  7. Kai-Wei Chang, Rajhans Samdani, and Dan Roth. 2013. A constrained latent variable model for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 601–612. find
  8. Aron Culotta, Michael Wick, Robert Hall, and Andrew McCallum. 2006. First-order probabilistic models for coreference resolution. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 81–88. find
  9. Hal Daumé III and Daniel Marcu. 2005. A large-scale exploration of effective global features for a joint entity detection and tracking model. In Empirical Methods in Natural Language Processing (EMNLP), pages 97–104. find
  10. Hal Daumé III, John Langford, and Daniel Marcu. 2009. Search-based structured prediction. Machine Learning, 75(3):297–325. find
  11. Pascal Denis and Jason Baldridge. 2007a. Joint determination of anaphoricity and coreference resolution using integer programming. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 236–243. find
  12. Pascal Denis and Jason Baldridge. 2007b. A ranking approach to pronoun resolution. In International Joint Conferences on Artificial Intelligence (IJCAI), pages 1588–1593. find
  13. John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12:2121–2159. find
  14. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 1971–1982. find our card
  15. Greg Durrett and Dan Klein. 2014. A joint model for entity analysis: Coreference, typing, and linking. Transactions of the Association for Computational Linguistics (TACL), 2:477–490. find
  16. Eraldo Rezende Fernandes, Cı́cero Nogueira Dos Santos, and Ruy Luiz Milidiú. 2012. Latent structure perceptron with feature induction for unrestricted coreference resolution. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning - Shared Task, pages 41–48. find our card
  17. Jenny Rose Finkel and Christopher D Manning. 2008. Enforcing transitivity in coreference resolution. In Association for Computational Linguistics (ACL), Short Paper, pages 45–48. find
  18. Thomas Finley and Thorsten Joachims. 2005. Supervised clustering with support vector machines. In Proceedings of the 22nd international conference on Machine learning, pages 217–224. find
  19. Aria Haghighi and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 385–393. find
  20. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: the 90% solution. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 57–60. find
  21. Andrew Kehler. 1997. Probabilistic coreference in information extraction. In Empirical Methods in Natural Language Processing (EMNLP), pages 163– 173. find
  22. Heeyoung Lee, Yves Peirsman, Angel Chang, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2011. Stanford’s multi-pass sieve coreference resolution system at the conll-2011 shared task. In Proceedings of the Conference on Computational Natural Language Learning: Shared Task, pages 28–34. find our card
  23. Xiaoqiang Luo, Abe Ittycheriah, Hongyan Jing, Nanda Kambhatla, and Salim Roukos. 2004. A mention-synchronous coreference resolution algorithm based on the bell tree. In Association for Computational Linguistics (ACL), page 135. find
  24. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Empirical Methods in Natural Language Processing (EMNLP), pages 25–32. find our card
  25. Chao Ma, Janardhan Rao Doppa, J Walker Orr, Prashanth Mannem, Xiaoli Fern, Tom Dietterich, and Prasad Tadepalli. 2014. Prune-and-score: Learning for greedy coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP). find
  26. Andrew McCallum and Ben Wellner. 2003. Toward conditional models of identity uncertainty with application to proper noun coreference. In Proceedings of the IJCAI Workshop on Information Integration on the Web. find
  27. Andrew McCallum and Ben Wellner. 2005. Conditional models of identity uncertainty with application to noun coreference. In Advances in Neural Information Processing Systems (NIPS), pages 905– 912. find
  28. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Association of Computational Linguistics (ACL), pages 104–111. find our card
  29. Cristina Nicolae and Gabriel Nicolae. 2006. Bestcut: A graph algorithm for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 275–283. find
  30. Hoifung Poon and Pedro Domingos. 2008. Joint unsupervised coreference resolution with markov logic. In Empirical Methods in Natural Language Processing (EMNLP), pages 650–659. find
  31. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. Conll-2012 shared task: Modeling multilingual unrestricted coreference in ontonotes. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Conference on Computational Natural Language Learning - Shared Task, pages 1–40. find our card
  32. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 492–501. find our card
  33. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Empirical Methods in Natural Language Processing (EMNLP), pages 968–977. find
  34. Altaf Rahman and Vincent Ng. 2011. Narrowing the modeling gap: a cluster-ranking approach to coreference resolution. Journal of Artificial Intelligence Research (JAIR), pages 469–521. find
  35. Marta Recasens, Marie-Catherine de Marneffe, and Christopher Potts. 2013. The life and death of discourse entities: Identifying singleton mentions. In Human Language Technology and North American Association for Computational Linguistics (HLT-NAACL), pages 627–633. find
  36. Stéphane Ross, Geoffrey J Gordon, and J Andrew Bagnell. 2011. A reduction of imitation learning and structured prediction to no-regret online learning. In Artificial Intelligence and Statistics (AISTATS), pages 627–633. find
  37. 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
  38. Veselin Stoyanov and Jason Eisner. 2012. Easy-first coreference resolution. In COLING, pages 2519– 2534. find
  39. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Reconcile: A coreference resolution research platform. Computer Science Technical Report, Cornell University, Ithaca, NY. find
  40. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the 6th conference on Message understanding, pages 45–52. find our card
  41. Xiaofeng Yang, Jian Su, Jun Lang, Chew Lim Tan, Ting Liu, and Sheng Li. 2008. An entity-mention model for coreference resolution with inductive logic programming. In Association of Computational Linguistics (ACL), pages 843–851. find