Elamur Research⌕
☰
home / papers / 2017 / Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events

Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events

Summary

The paper addresses event coreference resolution: grouping event mentions that refer to the same real-world event, both within a document (WD) and across documents (CD). Earlier systems either merged related documents into one mega-document or ran WD clustering and then CD clustering. The authors propose a two-stage iterative model that alternates between the two link types.

In the first stage, separately trained WD and CD pairwise classifiers take turns merging clusters. After each merge, event arguments are pooled, so evidence gathered by one merge type helps the other in later rounds. The CD classifier uses stricter thresholds and also draws on surrounding context. In the second stage, the model exploits "second-order" relations: two clusters are merged when their mentions share dependency relations, or co-occur in sentences, with events already known to corefer.

Tested on the ECB+ corpus, the full model outperforms prior systems, including HDDCRP, on the joint WD and CD task. The approach shows that letting different link types inform each other helps resolve coreferent events with very different surface forms.

Key points

  • Preprocessing: Documents are first grouped with Affinity Propagation on tf-idf vectors built from proper nouns and verbs. On ECB+ this produced perfect document clusters.
  • Merge thresholds: Tuned at 0.6 for the WD classifier and 0.9 for the CD classifier. The first stage converged after three iterations, with scores rising each round.
  • Cross-document results: The full model reaches 63.6 CoNLL F1, compared with 58.7 for HDDCRP (Yang et al., 2015). Within-document results are also reported as better than prior systems.
  • Second-stage merges: This stage made 81 merges, mostly between lexically dissimilar mentions such as (unveil, announce) and (spark, trigger). It even linked antonym-like pairs such as (win, beat).
  • Main errors:
    • Missed links usually involve mentions with few local arguments.
    • False merges mostly join same-lemma mentions: 24 reporting-verb clusters and 13 light-verb clusters were merged wrongly.

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

37 papers of our library cite it (of the 140673 whose bibliographies we read); 20 of them have a page here, 17 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/d17-1226 · arXiv 1707.07344

@inproceedings{choubey2017event,
  title = {{Event Coreference Resolution by Iteratively Unfolding Inter-dependencies among Events}},
  author = {Choubey, Prafulla Kumar and Huang, Ruihong},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  year = {2017},
  doi = {10.18653/v1/d17-1226},
  eprint = {1707.07344},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/d17-1226}
}

References

34 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. David Ahn. 2006. The stages of event extraction. In Proceedings of the Workshop on Annotating and Reasoning about Time and Events, pages 1–8. Association for Computational Linguistics. find
  2. James Allan, Jaime G Carbonell, George Doddington, Jonathan Yamron, and Yiming Yang. 1998. Topic detection and tracking pilot study final report. 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. find our card
  4. Cosmin Adrian Bejan and Sanda Harabagiu. 2010. Unsupervised event coreference resolution with rich linguistic features. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 1412–1422. Association for Computational Linguistics. find our card
  5. Cosmin Adrian Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. Computational Linguistics, 40(2):311–347. find our card
  6. Lars Buitinck, Gilles Louppe, Mathieu Blondel, Fabian Pedregosa, Andreas Mueller, Olivier Grisel, Vlad Niculae, Peter Prettenhofer, Alexandre Gramfort, Jaques Grobler, Robert Layton, Jake VanderPlas, Arnaud Joly, Brian Holt, and Gaël Varoquaux. 2013. API design for machine learning software: experi… find
  7. Danqi Chen and Christopher D Manning. 2014. A fast and accurate dependency parser using neural networks. In EMNLP, pages 740–750. find our card
  8. Zheng Chen and Heng Ji. 2009. Graph-based event coreference resolution. In Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing, pages 54–57. Association for Computational Linguistics. find our card
  9. Zheng Chen, Heng Ji, and Robert Haralick. 2009. A pairwise event coreference model, feature impact and evaluation for event coreference resolution. In Proceedings of the workshop on events in emerging text types, pages 17–22. Association for Computational Linguistics. find our card
  10. François Chollet. 2015. Keras. https://github.com/fchollet/keras. ↗
  11. Kevin Clark and Christopher D Manning. 2015. Entity-centric coreference resolution with model stacking. find our card
  12. Kevin Clark and Christopher D Manning. 2016. Improving coreference resolution by learning entity-level distributed representations. find our card
  13. Agata Cybulska and Piek Vossen. 2014a. Guidelines for ecb+ annotation of events and their coreference. Technical report, Technical report, Technical Report NWR-2014-1, VU University Amsterdam. find
  14. Agata Cybulska and Piek Vossen. 2014b. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In LREC, pages 4545– 4552. find our card
  15. Agata Cybulska and Piek Vossen. 2015a. Translating granularity of event slots into features for event coreference resolution. In Proceedings of the 3rd Workshop on EVENTS at the NAACL-HLT, pages 1– 10. find our card
  16. Agata Cybulska and Piek Vossen. 2015b. bag of events approach to event coreference resolution. supervised classification of event templates. IJCLA, page 11. find
  17. Naomi Daniel, Dragomir Radev, and Timothy Allison. 2003. Sub-event based multi-document summarization. In Proceedings of the HLT-NAACL 03 on Text summarization workshop-Volume 5, pages 9–16. Association for Computational Linguistics. find
  18. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation, 9(8):1735–1780. find
  19. Kevin Humphreys, Robert Gaizauskas, and Saliha Azzam. 1997. Event coreference for information extraction. In Proceedings of a Workshop on Operational Factors in Practical, Robust Anaphora Resolution for Unrestricted Texts, pages 75–81. Association for Computational Linguistics. find our card
  20. Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012. Joint entity and event coreference resolution across documents. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 489–50… find our card
  21. Zhengzhong Liu, Jun Araki, Eduard H Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In LREC, pages 4539–4544. find our card
  22. Jing Lu, Deepak Venugopal, Vibhav Gogate, and Vincent Ng. 2016. Joint inference for event coreference resolution. find our card
  23. 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. Association for Computational Linguistics. find our card
  24. James Mayfield, David Alexander, Bonnie J Dorr, Jason Eisner, Tamer Elsayed, Tim Finin, Clayton Fink, Marjorie Freedman, Nikesh Garera, Paul McNamee, et al. 2009. Cross-document coreference resolution: A key technology for learning by reading. In AAAI Spring Symposium: Learning by Reading and Learni… find
  25. Srini Narayanan and Sanda Harabagiu. 2004. Question answering based on semantic structures. In Proceedings of the 20th international conference on Computational Linguistics, page 693. Association for Computational Linguistics. find
  26. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In EMNLP, volume 14, pages 1532– 1543. find
  27. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pag… find our card
  28. Sameer Singh, Karl Schultz, and Andrew McCallum. 2009. Bi-directional joint inference for entity resolution and segmentation using imperatively-defined factor graphs. Machine Learning and Knowledge Discovery in Databases, pages 414–429. 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. K. Toutanova, D. Klein, C. Manning, and Y. Singer. 2003. Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network. In Proceedings of HLT-NAACL 2003. find
  31. 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. Association for Computational Linguistics. find our card
  32. Sam Wiseman, Alexander M Rush, and Stuart M Shieber. 2016. Learning global features for coreference resolution. In Proceedings of NAACL-HLT, pages 994–1004. find our card
  33. Bishan Yang, Claire Cardie, and Peter Frazier. 2015. A hierarchical distance-dependent bayesian model for event coreference resolution. Transactions of the Association for Computational Linguistics, 3:517– 528. find
  34. Tongtao Zhang, Hongzhi Li, Heng Ji, and Shih-Fu Chang. 2015. Cross-document event coreference resolution based on cross-media features. In EMNLP, pages 201–206. find

↑ back to top

This page in Markdown →