Elamur Research⌕
☰
home / papers / 2019 / Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution

Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution

Summary

The paper addresses cross-document coreference resolution (CDCR), meaning the grouping of mentions of the same entities and events across a collection of texts. Earlier work on the ECB+ corpus handled events only. Building on the joint idea of Lee et al. (2012), the authors design a neural model that resolves entity and event coreference together. Each mention is encoded from three sources:

  • its span, using word embeddings plus a character-level LSTM;
  • its surrounding context, using ELMo;
  • vectors of the current clusters of related mentions, linked through SRL predicate-argument structure.

A learned pairwise scorer feeds agglomerative clustering. The model alternates between event and entity clustering, so decisions in one task inform the other. Gold mentions are assumed as input.

On ECB+ the model sets a new state of the art for event coreference. No earlier study had published entity coreference scores for ECB+, so its entity results are the first. The joint version beats its disjoint variant on both tasks. This shows that coreference between arguments and predicates can usefully guide each other, which matters for multi-text applications such as question answering.

Key points

  • On events, the joint model beats the previous best system (KCP, Kenyon-Dean et al., 2018) by 10.5 CoNLL F1. The disjoint variant alone already gains 9.5 points.
  • Joint modeling adds 1.2 CoNLL F1 for entities and 1 point for events over the disjoint model (p < 0.001). Against a strong lemma baseline with topic clustering, the gains are 3.8 points (entities) and 3 points (events).
  • The SRL-based argument vectors cover four roles: Arg0, Arg1, location and time. Ablations show that every representation component helps. The continuous argument vectors outperform the binary features of Lee et al. (2012).
  • Document pre-clustering into topics is nearly perfect on the ECB+ test set (V-measure 0.984).
  • Error analysis shows that wrong merges often share a head lemma. Predicate-argument extraction errors account for 12% of event errors. Code is released at github.com/shanybar/event_entity_coref_ecb_plus.

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 · Semantic role labeling

Cited by

60 papers of our library cite it (of the 140673 whose bibliographies we read); 23 of them have a page here, 37 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1409 · arXiv 1906.01753

@inproceedings{barhom2019revisiting,
  title = {{Revisiting Joint Modeling of Cross-document Entity and Event Coreference Resolution}},
  author = {Barhom, Shany and Shwartz, Vered and Eirew, Alon and Bugert, Michael and Reimers, Nils and Dagan, Ido},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1409},
  eprint = {1906.01753},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/p19-1409}
}

References

40 references, 23 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. 1998a. Algorithms for scoring coreference chains. In The first international conference on language resources and evaluation workshop on linguistics coreference, volume 1, pages 563–566. Granada. find our card
  2. Cosmin 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, Uppsala, Sweden. Association for Computational Linguistics. find our card
  3. Amit Bagga and Breck Baldwin. 1998b. Entity-based cross-document coreferencing using the vector space model. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, ACL ’98/COL-ING ’98, page… find
  4. Prafulla Kumar Choubey and Ruihong Huang. 2017. Event coreference resolution by iteratively unfolding inter-dependencies among events. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2124–2133, Copenhagen, Denmark. Association for Computational Lingui… 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. Agata Cybulska and Piek Vossen. 2014. Using a sledgehammer to crack a nut? lexical diversity and event coreference resolution. In Proceedings of the 9th international conference on Language Resources and Evaluation (LREC). find our card
  7. Kevin Clark and Christopher D. Manning. 2016. Improving coreference resolution by learning entity-level distributed representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 643–653, Berlin, Germany. Association for Com… find our card
  8. Agata Cybulska and Piek Vossen. 2015a. ” bag of events” approach to event coreference resolution. supervised classification of event templates. Int. J. Comput. Linguistics Appl., 6(2):11–27. find
  9. Agata Cybulska and Piek Vossen. 2015b. Translating granularity of event slots into features for event coreference resolution. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation, pages 1–10, Denver, Colorado. Association for Computational Linguist… find our card
  10. Greg Durrett and Dan Klein. 2013. Easy victories and uphill battles in coreference resolution. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1971–1982, Seattle, Washington, USA. Association for Computational Linguistics. 687–692, New Orleans, Louisi… find our card
  11. Sourav Dutta and Gerhard Weikum. 2015. Cross-document co-reference resolution using sample-based clustering with knowledge enrichment. Transactions of the Association for Computational Linguistics, 3:15–28. find our card
  12. 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, Vancouver, British Columbia, Canada. Association for Computational Linguistics. find our card
  13. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Comput., 9(8):1735– 1780. find
  14. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of machine learning research, 9(Nov):2579–2605. find
  15. Matthew Honnibal and Ines Montani. 2017. spacy 2: Natural language understanding with bloom embeddings, convolutional neural networks and incremental parsing. To appear. find
  16. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Association for Computational Linguistics (ACL) System Demonstrations, pages 55–60. find our card
  17. Kian Kenyon-Dean, Jackie Chi Kit Cheung, and Doina Precup. 2018. Resolving event coreference with supervised representation learning and clustering-oriented regularization. In Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics, pages 1–10, New Orleans, Louisiana. Asso… find our card
  18. Daniel Khashabi, Snigdha Chaturvedi, Michael Roth, Shyam Upadhyay, and Dan Roth. 2018. Looking beyond the surface: A challenge set for reading comprehension over multiple sentences. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics:… find our card
  19. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. find
  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. George A Miller. 1995. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39– 41. find our card
  22. Vinod Nair and Geoffrey E Hinton. 2010. Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning (ICML-10), pages 807–814. find
  23. Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan, Edward Yang, Zachary DeVito, Zeming Lin, Alban Desmaison, Luca Antiga, and Adam Lerer. 2017. Automatic differentiation in pytorch. In NIPS-W. find
  24. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:282… find
  25. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global vectors for word representation. In Empirical Methods in Natural Language Processing (EMNLP), pages 1532– 1543. find
  26. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. Association for Computational Linguistics. find our card
  27. Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technolog… find
  28. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages Mart… find our card
  29. 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
  30. Delip Rao, Paul McNamee, and Mark Dredze. 2010. Streaming cross document entity coreference resolution. In Coling 2010: Posters, pages 1050–1058, Beijing, China. find our card
  31. Coling 2010 Organizing Committee. find
  32. Peter J Rousseeuw. 1987. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20:53–65. find
  33. Wei Shen, Jianyong Wang, and Jiawei Han. 2015. Entity linking with a knowledge base: Issues, techniques, and solutions. IEEE Transactions on Knowledge and Data Engineering, 27(2):443–460. find
  34. 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
  35. Shyam Upadhyay, Nitish Gupta, Christos Christodoulopoulos, and Dan Roth. 2016. Revisiting the evaluation for cross document event coreference. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1949–1958, Osaka, Japan. find our card
  36. The COLING 2016 Organizing Committee. find
  37. 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
  38. Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. Constructing datasets for multi-hop reading comprehension across documents. Transactions of the Association of Computational Linguistics, 6:287–302. find our card
  39. 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
  40. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William Cohen, Ruslan Salakhutdinov, and Christopher D. Manning. 2018. Hotpotqa: A dataset for diverse, explainable multi-hop question answering. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369… find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/barhom-2019-revisiting-joint-modeling-cross-document/