Elamur Research
☰
home / papers / 2020 / Event Extraction by Answering (Almost) Natural Questions

Event Extraction by Answering (Almost) Natural Questions

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/2020.emnlp-main.49.pdf

Summary

Event extraction means finding the word that signals an event (the trigger), assigning it an event type, and pulling out the text spans that fill that type's semantic roles. Earlier systems usually recognize entities first and then label them with roles. Entity recognition errors therefore carry into argument extraction, and similar roles across event types share no knowledge. Du and Cardie recast the task as extractive question answering using two BERT models. The first receives a generic query such as "action" or "verb" and tags each token with an event type. The second answers role-specific questions (for example, who bought something in a sale) by predicting the start and end of argument spans. A dynamic threshold decides how many spans to keep. Questions come from simple rules, and the richest version reuses role descriptions from the ACE annotation guidelines. On ACE 2005 the method outperforms earlier systems for both triggers and arguments, needs no entity annotation, and can extract roles never seen in training.

Key points

  • Two components share the input format [CLS] <question> [SEP] <sentence> [SEP]. BERT_QA_Trigger labels tokens with an event type or None. BERT_QA_Arg predicts start and end offsets of argument spans.

  • Trigger detection was tested with four fixed queries: "what is the trigger", "trigger", "action" and "verb".

  • Argument questions come from three templates:

    • the bare role name;
    • a WH-word question (who for persons, where for places, what otherwise);
    • a question built from the ACE annotation guidelines.

    Each template can optionally end with "in <trigger>".

  • Evaluation is on the ACE 2005 corpus. The approach skips the entity recognition step entirely and works in a zero-shot setting for unseen argument roles. More natural questions gave better results.

  • Code and question templates are released at github.com/xinyadu/eeqa.

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: Natural language processing

Cited by

196 papers of our library cite it (of the 140673 whose bibliographies we read); 6 of them have a page here, 190 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.emnlp-main.49

@inproceedings{du2020event,
  title = {{Event Extraction by Answering (Almost) Natural Questions}},
  author = {Du, Xinya and Cardie, Claire},
  booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2020},
  doi = {10.18653/v1/2020.emnlp-main.49},
  url = {https://doi.org/10.18653/v1/2020.emnlp-main.49}
}

References

27 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Yubo Chen, Liheng Xu, Kang Liu, Daojian Zeng, and Jun Zhao. 2015. Event extraction via dynamic multi-pooling convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Proces… find
  2. Massimiliano Ciaramita and Yasemin Altun. 2006. Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing, pages 594–602. find
  3. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  4. George R Doddington, Alexis Mitchell, Mark A Przybocki, Lance A Ramshaw, Stephanie M Strassel, and Ralph M Weischedel. 2004. The automatic content extraction (ace) program-tasks, data, and evaluation. In Lrec, volume 2, page 1. Lisbon. find
  5. Xinya Du and Claire Cardie. 2020. Document-level event role filler extraction using multi-granularity contextualized encoding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8010–8020, Online. Association for Computational Linguistics. find
  6. Xinya Du, Junru Shao, and Claire Cardie. 2017. Learning to ask: Neural question generation for reading comprehension. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1342–1352, Vancouver, Canada. Association for Computational… find our card
  7. Ralph Grishman and Beth Sundheim. 1996. Message Understanding Conference- 6: A brief history. In COLING 1996 Volume 1: The 16th International Conference on Computational Linguistics. find
  8. Michael Heilman. 2011. Automatic factual question generation from text. Ph.D. thesis, Ph. D. thesis, Carnegie Mellon University. find
  9. Michael Heilman and Noah A Smith. 2010. Good question! statistical ranking for question generation. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 609– 617. find
  10. Lifu Huang, Heng Ji, Kyunghyun Cho, Ido Dagan, Sebastian Riedel, and Clare Voss. 2018. Zero-shot transfer learning for event extraction. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2160–2170, Melbourne, Australia. Associat… find
  11. Ruihong Huang and Ellen Riloff. 2011. Peeling back the layers: Detecting event role fillers in secondary contexts. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1137–1147, Portland, Oregon, USA. Association for Computat… find
  12. Heng Ji and Ralph Grishman. 2008. Refining event extraction through cross-document inference. In Proceedings of ACL-08: HLT, pages 254–262, Columbus, Ohio. Association for Computational Linguistics. find
  13. Mandar Joshi, Eunsol Choi, Daniel Weld, and Luke Zettlemoyer. 2017. TriviaQA: A large scale distantly supervised challenge dataset for reading comprehension. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1601–1611, Vancouver… find our card
  14. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, et al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistic… find our card
  15. Omer Levy, Minjoon Seo, Eunsol Choi, and Luke Zettlemoyer. 2017. Zero-shot relation extraction via reading comprehension. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 333–342, Vancouver, Canada. Association for Computational Linguistics. find
  16. Qi Li, Heng Ji, and Liang Huang. 2013. Joint event extraction via structured prediction with global features. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 73–82, Sofia, Bulgaria. Association for Computational Linguistics. find
  17. Xiaoya Li, Jingrong Feng, Yuxian Meng, Qinghong Han, Fei Wu, and Jiwei Li. 2020. A unified MRC framework for named entity recognition. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5849– 5859, Online. Association for Computational Linguistics. find our card
  18. Xiaoya Li, Fan Yin, Zijun Sun, Xiayu Li, Arianna Yuan, Duo Chai, Mingxin Zhou, and Jiwei Li. 2019. find
  19. Entity-relation extraction as multi-turn question answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1340–1350, Florence, Italy. Association for Computational Linguistics. find
  20. Ying Lin, Heng Ji, Fei Huang, and Lingfei Wu. 2020. A joint neural model for information extraction with global features. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7999–8009, Online. Association for Computational Linguistics. find our card
  21. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2383–2392, Austin, Texas. Association for Computational Linguistics. find our card
  22. Ellen Riloff. 1996. Automatically generating extraction patterns from untagged text. In Proceedings of the national conference on artificial intelligence, pages 1044–1049. find
  23. Lei Sha, Feng Qian, Baobao Chang, and Zhifang Sui. 2018. Jointly extracting event triggers and arguments by dependency-bridge rnn and tensor-based argument interaction. In Thirty-Second AAAI Conference on Artificial Intelligence. find
  24. (LDC) Linguistic Data Consortium. 2005. English annotation guidelines for events. https://www.ldc.upenn.edu/sites/ www.ldc.upenn.edu/files/ english-events-guidelines-v5.4.3.pdf. ↗
  25. Beth M Sundheim. 1992. Overview of the fourth message understanding evaluation and conference. In Xiao Liu, Zhunchen Luo, and Heyan Huang. 2018. Proceedings of the 4th conference on Message un-Jointly multiple events extraction via attention-derstanding, pages 3–21. Association for Computa-based gra… find our card
  26. Ace 2005 multilin-neural networks. In Proceedings of the 2016 Con-gual training corpus. Linguistic Data Consortium, ference of the North American Chapter of the As-Philadelphia, 57. sociation for Computational Linguistics: Human Language Technologies, pages 300–309, San Diego, Bishan Yang and Tom M.… find
  27. Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word rep-Yue Zhang and Stephen Clark. 2011. Syntactic pro-resentations. In Proceedings of the 2018 Confer-cessing using the generalized perceptron and beam ence of the North American Chapter of the Associ-search.… find