Elamur Research
☰
home / papers / 2021 / Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/2021.acl-long.217.pdf

Summary

Event extraction turns sentences into structured records: an event type, a trigger, and role-labelled arguments. Most prior systems split this into separate subtasks such as entity recognition, trigger detection and argument classification. That approach needs fine-grained token-level labels and hand-designed pipelines or joint architectures, which can propagate errors. Text2Event replaces this with a single model that generates the structure directly. Event records are converted into a bracketed tree string, and a pre-trained T5 encoder-decoder learns to produce that string from raw text, writing labels as ordinary words. Training needs only sentence–record pairs. At inference time, a schema-guided constrained decoder keeps outputs valid. A curriculum first trains on simpler substructures before full events. Experiments on ACE and ERE show results comparable to earlier state-of-the-art systems in both supervised and transfer settings, without entity annotations. This suggests generative structure prediction is a practical, data-efficient alternative for information extraction.

Key points

  • Linearization: each event becomes a tree with a virtual Root, then event types, then roles, with text spans as leaves. The tree is flattened depth-first using "(" and ")" markers, and sentences with no event map to "()".
  • Training and decoding: the backbone is T5. Constrained decoding injects event-schema knowledge so the output cannot contain invalid types or role mismatches. The curriculum moves from trigger generation to independent argument generation, then to full structures.
  • Ablations (ACE05-EN dev, T5-base):
    • With full data, the curriculum variant reaches 71.4 Trig-C F1 and 53.3 Arg-C F1.
    • Swapping label names for meaningless symbols drops scores to 55.5 and 28.9.
    • Curriculum learning adds about 4.7 Trig-C F1 and 5.8 Arg-C F1 on average.
  • Low-resource and transfer results: constrained decoding helps most when only 1–5% of training data is used. In transfer learning, the model gains 3.7 Trig-C F1 and 3.2 Arg-C F1 without relying on shared entity labels.
  • Code: released at github.com/luyaojie/text2event.

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

141 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 138 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.acl-long.217

@inproceedings{lu2021text2event,
  title = {{Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction}},
  author = {Lu, Yaojie and Lin, Hongyu and Xu, Jin and Han, Xianpei and Tang, Jialong and Li, Annan and Sun, Le and Liao, Meng and Chen, Shaoyi},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.217},
  url = {https://doi.org/10.18653/v1/2021.acl-long.217}
}

References

57 references, 6 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, Sydney, Australia. Association for Computational Linguistics. find
  2. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In The Third International Conference on Learning Representations. find our card
  3. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum learning. In Proceedings of the 26th International Conference on Machine Learning, pages 41–48, Montreal. Omnipress. find our card
  4. Nicola De Cao, Gautier Izacard, Sebastian Riedel, and Fabio Petroni. 2021. Autoregressive entity retrieval. In International Conference on Learning Representations. find
  5. Pinzhen Chen, Nikolay Bogoychev, Kenneth Heafield, and Faheem Kirefu. 2020a. Parallel sentence mining by constrained decoding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1672–1678, Online. Association for Computational Linguistics. find
  6. 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
  7. Yunmo Chen, Tongfei Chen, Seth Ebner, Aaron Steven White, and Benjamin Van Durme. 2020b. Reading the manual: Event extraction as definition comprehension. In Proceedings of the Fourth Workshop on Structured Prediction for NLP, pages 74–83, Online. Association for Computational Linguistics. find
  8. George Doddington, Alexis Mitchell, Mark Przybocki, Lance Ramshaw, Stephanie Strassel, and Ralph Weischedel. 2004. The automatic content extraction (ACE) program – tasks, data, and evaluation. In Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04), Lisbo… find
  9. Li Dong and Mirella Lapata. 2016. Language to logical form with neural attention. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 33–43, Berlin, Germany. Association for Computational Linguistics. find
  10. Xinya Du and Claire Cardie. 2020. Event extraction by answering (almost) natural questions. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 671–683, Online. Association for Computational Linguistics. find our card
  11. Xinya Du, Alexander Rush, and Claire Cardie. 2021. GRIT: Generative role-filler transformers for document-level event entity extraction. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 634–644, Online. Association for… find
  12. Yu Hong, Jianfeng Zhang, Bin Ma, Jianmin Yao, Guodong Zhou, and Qiaoming Zhu. 2011. Using cross-entity inference to improve event extraction. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1127–1136, Portland, Oregon, US… find
  13. Yu Hong, Wenxuan Zhou, Jingli Zhang, Guodong Zhou, and Qiaoming Zhu. 2018. Self-regulation: Employing a generative adversarial network to improve event detection. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 515–526, Melbou… find
  14. Lifu Huang, Taylor Cassidy, Xiaocheng Feng, Heng Ji, Clare R. Voss, Jiawei Han, and Avirup Sil. 2016. find
  15. Liberal event extraction and event schema induction. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 258–268, Berlin, Germany. Association for Computational Linguistics. find
  16. 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
  17. Ruihong Huang and Ellen Riloff. 2012. Modeling textual cohesion for event extraction. In Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, AAAI’12, page 1664–1670. AAAI Press. find
  18. Heng Ji and Ralph Grishman. 2008. Refining event extraction through cross-document inference. In Proceedings of ACL-08: HLT, pages 254–262. Association for Computational Linguistics. find
  19. Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent continuous translation models. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1700–1709, Seattle, Washington, USA. Association for Computational Linguistics. find
  20. Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, and Yong Zhu. 2020. Event extraction as multi-turn question answering. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 829–838, Online. Association for Computational Linguistics. find
  21. Qi Li, Heng Ji, Yu Hong, and Sujian Li. 2014. Constructing information networks using one single model. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1846–1851, Doha, Qatar. Association for Computational Linguistics. find
  22. 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
  23. Shasha Liao and Ralph Grishman. 2010. Using document level cross-event inference to improve event extraction. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 789–797, Uppsala, Sweden. Association for Computational Linguistics. find
  24. Hongyu Lin, Yaojie Lu, Xianpei Han, and Le Sun. 2018. Nugget proposal networks for Chinese event detection. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1565–1574, Melbourne, Australia. Association for Computational Linguis… find
  25. 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
  26. Jian Liu, Yubo Chen, Kang Liu, Wei Bi, and Xiaojiang Liu. 2020. Event extraction as machine reading comprehension. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1641–1651, Online. Association for Computational Linguistics. find our card
  27. Xiao Liu, Zhunchen Luo, and Heyan Huang. 2018. Jointly multiple events extraction via attention-based graph information aggregation. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1247–1256, Brussels, Belgium. Association for Computational Linguistic… find
  28. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In Seventh International Conference on Learning Representations. find
  29. Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, and Houfeng Wang. 2019. Exploring sequence-to-sequence learning in aspect term extraction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3538– 3547, Florence, Italy. Association for Computational Linguis… find
  30. Jie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros, and Yaser Al-Onaizan. 2020. Resource-enhanced neural model for event argument extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3554–3559, Online. Association for Computational Linguistics. find
  31. David McClosky, Mihai Surdeanu, and Christopher Manning. 2011. Event extraction as dependency parsing. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 1626–1635, Portland, Oregon, USA. Association for Computational Lingui… find
  32. Rafael Müller, Simon Kornblith, and Geoffrey E Hinton. 2019. When does label smoothing help? In Advances in Neural Information Processing Systems, volume 32, pages 4694–4703. Curran Associates, Inc. find
  33. Thien Huu Nguyen, Kyunghyun Cho, and Ralph Grishman. 2016. Joint event extraction via recurrent neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 300–309, San Diego, California. As… find
  34. Trung Minh Nguyen and Thien Huu Nguyen. 2019. One for all: Neural joint modeling of entities and events. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI ’2019. Association for the Advancement of Artificial Intelligence. find
  35. Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos Santos, Bing Xiang, and Stefano Soatto. 2021. Structured prediction as translation between augmented natural languages. In The Ninth International Conference on Learning Representations. find
  36. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140):1–67. find
  37. Lei Sha, Jing Liu, Chin-Yew Lin, Sujian Li, Baobao Chang, and Zhifang Sui. 2016. RBPB: Regularization-based pattern balancing method for event extraction. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1224–1234, Berlin, Germ… find
  38. Linfeng Song, Ante Wang, Jinsong Su, Yue Zhang, Kun Xu, Yubin Ge, and Dong Yu. 2020. Structural information preserving for graph-to-text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7987– 7998, Online. Association for Computational Lin… find
  39. Jana Straková, Milan Straka, and Jan Hajic. 2019. Neural architectures for nested NER through linearization. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5326–5331, Florence, Italy. Association for Computational Linguistics. find
  40. Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems, volume 27, pages 3104–3112. Curran Associates, Inc. find
  41. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. 2016. Rethinking the inception architecture for computer vision. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818–2826. find
  42. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Ł ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, volume 30, pages 5998–6008. Curran Associates, Inc. find
  43. Oriol Vinyals, Ł ukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. 2015. Grammar as a foreign language. In Advances in Neural Information Processing Systems, volume 28, pages 2773–2781. Curran Associates, Inc. find
  44. David Wadden, Ulme Wennberg, Yi Luan, and Hannaneh Hajishirzi. 2019. Entity, relation, and event extraction with contextualized span representations. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Langua… find our card
  45. Christopher Walker, Stephanie Strassel, Julie Medero, and Kazuaki Maeda. 2006. find
  46. Ace 2005 multilingual training corpus. find
  47. Xiaozhi Wang, Ziqi Wang, Xu Han, Zhiyuan Liu, Juanzi Li, Peng Li, Maosong Sun, Jie Zhou, and Xiang Ren. 2019. HMEAE: Hierarchical modular event argument extraction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on… find
  48. Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, and Yongdong Zhang. 2020. Curriculum learning for natural language understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6095–6104, Online. Association for Computational Lingui… find
  49. Bishan Yang and Tom M. Mitchell. 2016. Joint extraction of events and entities within a document context. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 289–299, San Diego, California. Associati… find
  50. Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, and Dongsheng Li. 2019. Exploring pre-trained language models for event extraction and generation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5284– 5294, Florence, Italy. Association for Computation… find
  51. Xiangrong Zeng, Daojian Zeng, Shizhu He, Kang Liu, and Jun Zhao. 2018. Extracting relational facts by an end-to-end neural model with copy mechanism. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 506–514, Melbourne, Australi… find
  52. Hongming Zhang, Haoyu Wang, and Dan Roth. 2020a. Unsupervised label-aware event trigger and argument classification. find
  53. Junchi Zhang, Yanxia Qin, Yue Zhang, Mengchi Liu, and Donghong Ji. 2019a. Extracting entities and events as a single task using a transition-based neural model. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 5422–5428. International Joi… find
  54. Ranran Haoran Zhang, Qianying Liu, Aysa Xuemo Fan, Heng Ji, Daojian Zeng, Fei Cheng, Daisuke Kawahara, and Sadao Kurohashi. 2020b. Minimize exposure bias of Seq2Seq models in joint entity and relation extraction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 236–246… find
  55. Tongtao Zhang, Heng Ji, and Avirup Sil. 2019b. Joint entity and event extraction with generative adversarial imitation learning. Data Intelligence, 1(2):99– 120. find
  56. Zhisong Zhang, Xiang Kong, Zhengzhong Liu, Xuezhe Ma, and Eduard Hovy. 2020c. A two-step approach for implicit event argument detection. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7479–7485, Online. Association for Computational Linguistics. find
  57. Shun Zheng, Wei Cao, Wei Xu, and Jiang Bian. 2019. Doc2EDAG: An end-to-end document-level framework for Chinese financial event extraction. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Process… find