Elamur Research⌕
☰
home / papers / 2016 / Joint Inference for Event Coreference Resolution

Joint Inference for Event Coreference Resolution

Summary

Resolving which event mentions in a document describe the same real-world event is difficult. Event coreference sits near the end of the information extraction pipeline, so it inherits errors from earlier steps such as trigger detection, argument extraction and entity coreference. The authors argue that modelling these steps together lets them correct one another. They build what they describe as the first Markov Logic Network (MLN) for event coreference. It jointly handles four tasks: trigger identification with subtyping, argument and role detection, entity coreference, and event coreference.

Writing rich NLP features directly as MLN formulas would make inference and learning intractable. Instead, the classifier outputs are compressed into low-dimensional weighted unit clauses and combined with the logical formulas at inference time. The system was tested on the English KBP 2015 corpus and the Chinese part of ACE 2005. On both, it significantly outperforms a pipeline baseline, mainly by finding more coreference links (higher recall). On KBP it sets a new best result. The unit-clause technique could apply to other MLN-based NLP tasks.

Key points

  • Datasets:
    • KBP 2015 English: training set of 158 documents with 6538 event mentions in 3335 chains; test set of 202 documents with 6438 mentions in 4125 chains.
    • ACE 2005 Chinese: 633 documents with 3333 mentions in 2521 chains.
  • Ontologies and guidelines: ACE uses 33 event subtypes and KBP uses 38, with 31 shared. KBP allows multi-word triggers and has a looser coreference definition, since ACE also requires the arguments to be coreferent.
  • Baseline: a five-step pipeline using CRF++ for entity extraction and English triggers, and SVM light for entity coreference and Chinese triggers.
  • Main result: on KBP, average F1 beats the previous best result by about 0.43 points. The gains come from higher recall, notably on links between lexically different triggers and between distant mentions.
  • Remaining errors:
    • Precision: frequent words that are wrongly tagged as triggers, and arguments that are missed when they fall outside the trigger's sentence.
    • Recall: unseen or rare triggers, and lack of knowledge to link lexically different triggers, especially in Chinese.

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

19 papers of our library cite it (of the 140673 whose bibliographies we read); 7 of them have a page here, 12 not yet.

Cite

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

@inproceedings{lu2016joint,
  title = {{Joint Inference for Event Coreference Resolution}},
  author = {Lu, Jing and Venugopal, Deepak and Gogate, Vibhav and Ng, Vincent},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  year = {2016},
  url = {https://aclanthology.org/C16-1308/}
}

References

35 references, 17 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. find
  2. Jun Araki and Teruko Mitamura. 2015. Joint event trigger identification and event coreference resolution with structured perceptron. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2074–2080. find our card
  3. Jun Araki, Zhengzhong Liu, Eduard Hovy, and Teruko Mitamura. 2014. Detecting subevent structure for event coreference resolution. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4553–4558. find our card
  4. Amit Bagga and Breck Baldwin. 1998. Algorithms for scoring coreference chains. In Proceedings of the Linguistic Coreference Workshop at The First International Conference on Language Resources and Evaluation, pages 563–566. find our card
  5. 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. find our card
  6. Cosmin Adrian Bejan and Sanda Harabagiu. 2014. Unsupervised event coreference resolution. Computational Linguistics, 40(2):311–347. find our card
  7. 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 (TextGraphs-4), pages 54–57. find our card
  8. Chen Chen and Vincent Ng. 2014. SinoCoreferencer: An end-to-end Chinese event coreference resolver. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4532–4538. find our card
  9. Chen Chen and Vincent Ng. 2016. Joint inference over a lightly supervised information extraction pipeline: Towards event coreference resolution for resource-scarce languages. In Proceedings of the 30th AAAI Conference on Artificial Intelligence, pages 2913–2920. find
  10. Bin Chen, Jian Su, Sinno Jialin Pan, and Chew Lim Tan. 2011. A unified event coreference resolution by integrating multiple resolvers. In Proceedings of the 4th International Joint Conference on Natural Language Processing, pages 102–110. find our card
  11. Agata Cybulska and Piek Vossen. 2012. Using semantic relations to solve event coreference in text. In Proceedings of the LREC Workshop on Semantic Relations-II Enhancing Resources and Applications (SemRel 2012), pages 60–67. find
  12. Pedro Domingos and Daniel Lowd. 2009. Markov Logic: An Interface Layer for Artificial Intelligence. Morgan & Claypool, San Rafael, CA. find
  13. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA. find
  14. Vibhav Gogate and Pedro Domingos. 2011. Probabilistic theorem proving. In Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, pages 256–265. find
  15. Gurobi. 2013. Gurobi Optimizer Reference Manual. Gurobi Inc. find
  16. Yu Hong, Di Lu, Dian Yu, Xiaoman Pan, Xiaobin Wang, Yadong Chen, Lifu Huang, and Heng Ji. 2015. RPI BLENDER TAC-KBP2015 system description. In Proceedings of the Eighth Text Analysis Conference (TAC 2015). find
  17. 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
  18. Thorsten Joachims. 1999. Making large-scale SVM learning practical. In Bernhard Scholkopf and Alexander Smola, editors, Advances in Kernel Methods - Support Vector Learning, pages 44–56. MIT Press. find
  19. 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
  20. Peifeng Li, Guodong Zhou, Qiaoming Zhu, and Libin Hou. 2012. Employing compositional semantics and discourse consistency in chinese event extraction. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 100… find
  21. Zhengzhong Liu, Jun Araki, Eduard Hovy, and Teruko Mitamura. 2014. Supervised within-document event coreference using information propagation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation, pages 4539–4544. find our card
  22. 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. find our card
  23. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60. find our card
  24. Katie McConky, Rakesh Nagi, Moises Sudit, and William Hughes. 2012. Improving event co-reference by context extraction and dynamic feature weighting. In Proceedings of the 2012 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, pages 38… find
  25. Sean Monahan, Michael Mohler, Marc Tomlinson, Amy Book, Maxim Gorelkin, Kevin Crosby, and Mary Brunson. 2015. Populating a knowledge base with information about events. In Proceedings of the Eighth Text Analysis Conference (TAC 2015). find
  26. Nafise Sadat Moosavi and Michael Strube. 2016. Which coreference evaluation metric do you trust? a proposal for a link-based entity aware metric. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 632–642. find our card
  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. Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand Index for coreference evaluation. Natural Language Engineering, 17(4):485–510. find
  29. Sangeetha S. and Michael Arock. 2012. Event coreference resolution using mincut based graph clustering. International Journal of Computing and Information Sciences, pages 253–260. find
  30. Mark Sammons, Haoruo Peng, Yangqiu Song, Shyam Upadhyay, Chen-Tse Tsai, Pavankumar Reddyand, Subhro Roy, and Dan Roth. 2015. find
  31. Illinois CCG TAC 2015 event nugget, entity discovery and linking, and slot filler validation systems. In Proceedings of the Eighth Text Analysis Conference (TAC 2015). find
  32. 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
  33. Marc Vilain, John Burger, John Aberdeen, Dennis Connolly, and Lynette Hirschman. 1995. A model-theoretic coreference scoring scheme. In Proceedings of the Sixth Message Understanding Conference, pages 45–52. find our card
  34. Nianwen Xue and Martha Palmer. 2009. Adding semantic roles to the Chinese Treebank. Natural Language Engineering, 15(1):143–172. find
  35. 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

↑ back to top

This page in Markdown →