Elamur Research⌕
☰
home / papers / 2012 / Joint Entity and Event Coreference Resolution across Documents

Joint Entity and Event Coreference Resolution across Documents

Summary

Most coreference systems link only noun phrases that refer to entities. They miss links between events, such as a verb and a noun naming the same happening. Lee et al. address entities and events together, across multiple news documents.

The authors annotated and released a corpus with intra- and inter-document coreference links for both nominal and verbal mentions. Their pipeline works in stages:

  • It groups documents by topic.
  • It extracts nominal, pronominal and verbal mentions.
  • It applies high-precision sieves from the Stanford coreference system.
  • It then merges clusters cautiously and iteratively. A single linear regressor scores each candidate merge, and after every merge the features are recomputed.

Semantic-role features carry information both ways. If two events have arguments that already corefer, merging those events becomes more likely, and the reverse also holds.

The joint model scores more than 3 CoNLL F1 points above two strong baselines, each of which handles entity and event coreference in isolation. It improves on every standard metric. This matters for applications such as news aggregation, multi-document summarization and cross-document information extraction.

Key points

  • Merge rule: two clusters are merged only if the regressor scores the merge above 0.5. This means more than half of the newly linked mention pairs are predicted to be correct. Pronouns are handled afterwards by a separate deterministic sieve.
  • Verbal mentions: these are all VB* words except have, be and seem. Event nouns are matched to verbs through WordNet's "derivationally related form" relation. Document clustering uses the EM-based method of Surdeanu et al. (2005).
  • Evaluation: results are reported with MUC, B³, CEAF-φ4, BLANC and the official CoNLL-2011 metric. The joint model wins on all of them for both entities and events.
  • Error analysis: the authors manually inspected 100 errors and grouped them into nine types. The largest are:
    • pronoun resolution: 36%
    • semantics beyond role frames and WordNet: 20%
    • undetected arguments of nominal events: 17%
  • Features: among the most heavily weighted are those based on coreferent semantic-role arguments, for example "Coreferent Argument for Arg1".

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

100 papers of our library cite it (of the 140673 whose bibliographies we read); 37 of them have a page here, 63 not yet.

Cite

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

@inproceedings{lee2012joint,
  title = {{Joint Entity and Event Coreference Resolution across Documents}},
  author = {Lee, Heeyoung and Recasens, Marta and Chang, Angel and Surdeanu, Mihai and Jurafsky, Dan},
  booktitle = {Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning},
  year = {2012},
  url = {https://aclanthology.org/D12-1045/}
}

References

33 references, 21 of them with a card of ours. ↗ leads to the work, «find» 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 LREC 1998 Workshop on Linguistic Coreference, pages 563–566. find our card
  2. Amit Bagga and Breck Baldwin. 1999. Cross-document event coreference: Annotations, experiments, and observations. In Proceedings of the ACL 1999 Workshop on Coreference and Its Applications, pages 1–8. find our card
  3. Cosmin Bejan and Sanda Harabagiu. 2010. Unsupervised Event Coreference Resolution with Rich Linguistic Features. In Proceedings of ACL 2010, pages 1412–1422. find our card
  4. Eric Brill. 1995. Transformation-based error-driven learning and natural language processing: a case study in part of speech tagging. Computational Linguistics, 21(4):543–565. find our card
  5. Zheng Chen and Heng Ji. 2009. Graph-based event coreference resolution. In Proceedings of the ACL-IJCNLP 2009 Workshop on Graph-based Methods for Natural Language Processing, pages 54–57. find our card
  6. Pascal Denis and Jason Baldridge. 2007. Joint determination of anaphoricity and coreference resolution using integer programming. In Proceedings of NAACL-HLT 2007. find our card
  7. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge. find
  8. Aria Haghighi and Dan Klein. 2009. Simple coreference resolution with rich syntactic and semantic features. In Proceedings of EMNLP 2009, pages 1152–1161. find our card
  9. Aria Haghighi and Dan Klein. 2010. Coreference resolution in a modular, entity-centered model. In Proceedings of HLT-NAACL 2010, pages 385–393. find our card
  10. Tian He. 2007. Coreference Resolution on Entities and Events for Hospital Discharge Summaries. Thesis, Massachusetts Institute of Technology. find
  11. Jerry R. Hobbs. 1978. Resolving pronoun references. Lingua, 44(4):311–338. find our card
  12. Kevin Humphreys, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In Proceedings of the Workshop On Operational Factors In Practical Robust Anaphora Resolution For Unrestricted Texts, pages 75–81. find our card
  13. Klaus Krippendorff. 2004. Content Analysis: An Introduction to its Methodology. Sage, Thousand Oaks, CA, second edition. find
  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 CoNLL 2011: Shared Task, pages 28–34. find our card
  15. Dekang Lin. 1998. Automatic retrieval and clustering of similar words. In Proceedings of COLING-ACL 1998, pages 768–774. find
  16. Xiaoqiang Luo. 2005. On coreference resolution performance metrics. In Proceedings of HLT-EMNLP 2005, pages 25–32. find our card
  17. A. Meyers, R. Reeves, C. Macleod, R. Szekely, V. Zielinska, B. Young, and R. Grishman. 2004. The Nom-Bank project: an interim report. In Proceedings of the HLT-NAACL 2004 Workshop on Frontiers in Corpus Annotation, pages 24–31. find
  18. Rebecca Passonneau. 2004. Computing reliability for coreference annotation. In Proceedings of LREC 2004, pages 1503–1506. find
  19. Simone Paolo Ponzetto and Michael Strube. 2006. Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution. In Proceedings of HLT-NAACL 2006, pages 192–199. find our card
  20. Hoifung Poon and Pedro Domingos. 2008. Joint unsupervised coreference resolution with Markov logic. In Proceedings of EMNLP 2008, pages 650–659. find our card
  21. Sameer S. Pradhan, Lance Ramshaw, Ralph Weischedel, Jessica MacBride, and Linnea Micciulla. 2007. Unrestricted coreference: Identifying entities and events in OntoNotes. In Proceedings of ICSC 2007, pages 446–453. find
  22. Sameer Pradhan, Lance Ramshaw, Mitchell Marcus, Martha Palmer, Ralph Weischedel, and Nianwen Xue. 2011. CoNLL-2011 shared task: Modeling unrestricted coreference in OntoNotes. In Proceedings of CoNLL 2011: Shared Task, pages 1–27. find our card
  23. Karthik Raghunathan, Heeyoung Lee, Sudarshan Rangarajan, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky, and Chris Manning. 2010. A multi-pass sieve for coreference resolution. In Proceedings of EMNLP 2010, pages 492–501. find our card
  24. Altaf Rahman and Vincent Ng. 2011. Coreference resolution with world knowledge. In Proceedings of ACL 2011, pages 814–824. find our card
  25. William M. Rand. 1971. Objective criteria for the evaluation of clustering methods. Journal of the American Statistical Association, 66(336):846–850. find
  26. Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand index for coreference evaluation. Natural Language Engineering, 17(4):485–510. find
  27. 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 ACL-IJCNLP 2009, pages 656–664. find our card
  28. Mihai Surdeanu, Jordi Turmo, and Alicia Ageno. 2005. A hybrid unsupervised approach for document clustering. In Proceedings of KDD 2005, pages 685–690. find
  29. Mihai Surdeanu, Lluı́s Màrquez, Xavier Carreras, and Pere R. Comas. 2007. Combination strategies for semantic role labeling. Journal of Artificial Intelligence Research, 29:105–151. find
  30. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of MUC-6, pages 45–52. find our card
  31. Bonnie Lynn Webber. 1988. Discourse deixis: reference to discourse segments. In Proceedings of ACL 1988, pages 113–122. find our card
  32. Michael L. Wick, Khashayar Rohanimanesh, Karl Schultz, and Andrew McCallum. 2008. A unified approach for schema matching, coreference and canonicalization. In Proceedings of KDD 2008, pages 722– 730. find
  33. David Yarowsky. 1995. Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of ACL 1995, pages 189–196. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lee-2012-joint-entity-event-coreference-resolution/