Elamur Research⌕
☰
home / papers / 2014 / Limited memory incremental coreference resolution

Limited memory incremental coreference resolution

Summary

Coreference resolution groups mentions in a document into clusters that refer to the same real-world entity. Pairwise models often make locally plausible links that produce globally inconsistent clusters. Earlier remedies split into two separate lines of work: ranking-based decoding and cluster-level modelling. Webster and Curran merge these by treating coreference like shift-reduce parsing. Mentions are read once, in document order, from a queue. Each mention either starts a new entity on a stack of partial clusters (shift) or joins an existing cluster (reduce). This makes anaphoricity and antecedent choice a single joint decision.

The stack is read as an approximation of a reader's mental state. This supports discourse features inspired by Centering and Accessibility Theory, such as competition between candidate entities and depth in the stack. The system, LIMERIC, uses a max-margin averaged perceptron with optional beam search. It is trained and tested on predicted mentions from OntoNotes 5 (CoNLL-2012). It surpasses publicly available systems and rivals more complex research systems while needing little memory.

Key points

  • LIMERIC scores 63.33 CoNLL on the CoNLL-2012 DEV split and 62.91 on TEST (OntoNotes 5).
  • Training updates weights when it detects one of five error types:
    • three come from Durrett and Klein (2013);
    • two are inspired by Kummerfeld and Klein (2013).
  • Most correct merge targets sit near the top of the stack:
    • 78% lie within depth 10;
    • 88% lie within depth 20;
    • 97% lie within depth 60.
  • Capping the search at depth 60 still drops DEV to 61.31.
  • The final system uses a beam of up to 10 stacks with a new-stack threshold of 5. A single-beam setup remains competitive, so the rich features matter more than beam search.
  • In the feature analysis, competition and stack-depth features carry high weights, and surface features are the least useful.

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

9 papers of our library cite it (of the 140673 whose bibliographies we read); 5 of them have a page here, 4 not yet.

Cite

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

@inproceedings{webster2014limited,
  title = {{Limited memory incremental coreference resolution}},
  author = {Webster, Kellie and Curran, James R.},
  booktitle = {Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers},
  year = {2014},
  url = {https://aclanthology.org/C14-1201/}
}

References

27 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. A. V. Aho and S. C. Johnson. 1974. LR parsing. ACM Computing Surveys, 6(2):99–124. find
  2. Mira Ariel. 2001. Accessibility theory: An overview. Text representation: Linguistic and psycholinguistic aspects, pages 29–87. find
  3. 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, volume 1, pages 563– 566, Grenada, Spain. find our card
  4. Eric Bengtson and Dan Roth. 2008. Understanding the value of features for coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 294–303, Edinburgh, Scotland. find our card
  5. Kai-Wei Chang, Rajhans Samdani, and Dan Roth. 2013. A constrained latent variable model for coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 601–612, Seattle, Washington. find our card
  6. Pascal Denis, Jason Baldridge, et al. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In Proceedings of NAACL HLT, pages 236–243, Rochester, New York. find our card
  7. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 1971–1982, Seattle, Washington. find our card
  8. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, Massachusetts. find
  9. Eraldo Fernandes, Cı́cero dos Santos, and Ruy Milidiú. 2012. Latent structure perceptron with feature induction for unrestricted coreference resolution. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 41–48, Jeju Island, Korea. find our card
  10. David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. 2007. English gigaword (third edition), LDC catalog number LDC2003T05. find
  11. Barbara J. Grosz, Scott Weinstein, and Aravind K. Joshi. 1995. Centering: A framework for modeling the local coherence of discourse. Computational Linguistics, 21:203–225. find our card
  12. Manfred Klenner and Don Tuggener. 2011. An incremental entity-mention model for coreference resolution with restrictive antecedent accessibility. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 178–185, Hissar, Bulgaria. find our card
  13. Jonathan K Kummerfeld and Dan Klein. 2013. Error-driven analysis of challenges in coreference resolution. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 265–277, Seattle, Washington. find our card
  14. 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 Fifteenth Conference on Computational Natural Language Learning: Shared Task, pages 28–… find our card
  15. Thomas Lin, Oren Etzioni, et al. 2012. No noun phrase left behind: detecting and typing unlinkable entities. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 893–903, Seattle, Washington. find
  16. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 25–32, Vancouver, British Columbia. find our card
  17. Vincent Ng and Claire Cardie. 2002. Improving machine learning approaches to coreference resolution. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 104–111, Philadelphia, Pennsylvania. find our card
  18. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, wordnet and wikipedia for coreference resolution. In Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, pages 192–… find our card
  19. Sameer Pradhan, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. Conll-2012 shared task: Modeling multilingual unrestricted coreference in ontonotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island, Korea. find our card
  20. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nate Chambers, Mihai Surdeanu, Dan Jurafsky, and Christopher Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 492–501, Cambridge, Mas… find our card
  21. Altaf Rahman and Vincent Ng. 2009. Supervised models for coreference resolution. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2-Volume 2, pages 968–977, Edinburgh, Scotland. find our card
  22. Marta Recasens, Marie-Catherine de Marneffe, and Christopher Potts. 2013. The life and death of discourse entities: Identifying singleton mentions. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages… find
  23. 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
  24. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010a. Coreference resolution with reconcile. In Proceedings of the ACL 2010 Conference Short Papers, pages 156–161, Uppsala, Sweden. find our card
  25. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010b. Reconcile: A coreference resolution research platform. find
  26. 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, Columbia, Maryland. find our card
  27. Yue Zhang and Joakim Nivre. 2012. Analyzing the effect of global learning and beam-search on transition-based dependency parsing. In Proceedings of COLING 2012: Posters, pages 1391–1400, Bombay, India. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/webster-2014-limited-memory-incremental-coreference-resolution/