Elamur Research⌕
☰
home / papers / 2022 / DEGREE: A Data-Efficient Generation-Based Event Extraction Model

DEGREE: A Data-Efficient Generation-Based Event Extraction Model

Summary

Annotating events (triggers plus role-labelled arguments) is costly. ACE 2005, for instance, needed two rounds of expert annotation. This makes it hard to extend event extraction (EE) to new domains and event types. DEGREE addresses low-resource, end-to-end EE by recasting it as conditional text generation. The model fine-tunes a pre-trained generative encoder-decoder (Lewis et al., 2020). It takes a passage plus a hand-crafted prompt containing an event type description, a few keywords, and an E2E template. It then writes a natural sentence that fills the template's placeholders with the trigger and arguments. A deterministic parser and string matching map the output back to text spans. Inference runs once per event type. The prompt, built from the dataset's annotation guidelines, supplies label semantics and weak supervision. Joint generation lets trigger detection and argument extraction share knowledge. On ACE 2005 and ERE-EN, DEGREE clearly beats classification-based and generation-based baselines when training data is scarce. This shows that prompt-guided generation can reduce annotation needs, although template design still requires care.

Key points

  • Prompt and template design: The ED template has the form "Event trigger is <Trigger>". Each event type then gets its own EAE template, whose placeholders such as "somewhere" or "some attacker" hint at argument types. Multiple arguments for one role are joined with "and", and unfilled roles keep their placeholder.
  • Data efficiency (ACE05-E argument extraction): With 10% of the training data, DEGREE (EAE) reaches 57.3 Arg-C, compared with 45.4 for OneIE. With full data, it scores 73.5 Arg-C, versus 69.3 for OneIE and 66.7 for BART-Gen.
  • Value of natural-language placeholders: Replacing them with special tokens costs more than 1 F1, which supports the benefit of label semantics.
  • Sensitivity to templates: Alternative templates change results (e.g., 55.5 and 56.9 Arg-C at 10% data), yet still outperform OneIE and BART-Gen. Automating template construction is left for future work.
  • Availability: Code and models are released at github.com/PlusLabNLP/DEGREE.

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

90 papers of our library cite it (of the 140884 whose bibliographies we read); 2 of them have a page here, 88 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.naacl-main.138

@inproceedings{hsu2022degree,
  title = {{DEGREE: A Data-Efficient Generation-Based Event Extraction Model}},
  author = {Hsu, I-Hung and Huang, Kuan-Hao and Boschee, Elizabeth and Miller, Scott and Natarajan, Prem and Chang, Kai-Wei and Peng, Nanyun},
  booktitle = {Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2022},
  doi = {10.18653/v1/2022.naacl-main.138},
  url = {https://doi.org/10.18653/v1/2022.naacl-main.138}
}

References

40 references, 21 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. find our card
  2. Jonathan Berant, Vivek Srikumar, Pei-Chun Chen, Abby Vander Linden, Brittany Harding, Brad Huang, Peter Clark, and Christopher D. Manning. 2014. Modeling biological processes for reading comprehension. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). find our card
  3. Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Yubin Wang, and Bin Wang. 2021. Few-shot event detection with prototypical amortized conditional random field. In Findings of the Association for Computational Linguistics: ACL/IJCNLP. find
  4. Shumin Deng, Ningyu Zhang, Jiaojian Kang, Yichi Zhang, Wei Zhang, and Huajun Chen. 2020. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection. In The Thirteenth ACM International Conference on Web Search and Data Mining (WSDM). find
  5. Kung-Hsiang Huang, Sam Tang, and Nanyun Peng. 2021. Document-level entity-based extraction as template generation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event / Punta Cana, Dominican Republic, 7-11 November, 2021. find
  6. 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 Proceedings of the Fourth International Conference on Language Resources and Evaluation (… find our card
  7. Kung-Hsiang Huang, Mu Yang, and Nanyun Peng. 2020. Biomedical event extraction with hierarchical knowledge graphs. In the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)-Findings, short. find
  8. 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). find our card
  9. Steven Fincke, Shantanu Agarwal, Scott Miller, and Elizabeth Boschee. 2021. Language model priming for cross-lingual event extraction. arXiv preprint arXiv:2109.12383. — [arXiv:2109.12383](https://arxiv.org/abs/2109.12383) find
  10. Rujun Han, I-Hung Hsu, Jiao Sun, Julia Baylon, Qiang Ning, Dan Roth, and Nanyun Peng. 2021. ESTER: A machine reading comprehension dataset for reasoning about event semantic relations. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Even… find
  11. Rujun Han, I-Hung Hsu, Mu Yang, Aram Galstyan, Ralph M. Weischedel, and Nanyun Peng. 2019a. Deep structured neural network for event temporal relation extraction. In Proceedings of the 23rd Conference on Computational Natural Language Learning, CoNLL 2019, Hong Kong, China, November 3-4, 2019. find
  12. Rujun Han, Qiang Ning, and Nanyun Peng. 2019b. Joint event and temporal relation extraction with shared representations and structured prediction. In 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP). find
  13. Frederik Hogenboom, Flavius Frasincar, Uzay Kaymak, Franciska de Jong, and Emiel Caron. 2016. A survey of event extraction methods from text for decision support systems. Decis. Support Syst., 85:12–22. find
  14. Kuan-Hao Huang, I-Hung Hsu, Premkumar Natarajan, Kai-Wei Chang, and Nanyun Peng. 2022. Multilingual generative language models for zero-shot cross-lingual event argument extraction. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL). find
  15. Kung-Hsiang Huang and Nanyun Peng. 2021. Document-level event extraction with efficient end-to-end learning of cross-event dependencies. In The 3rd Workshop on Narrative Understanding (NAACL 2021). find
  16. Heng Ji and Ralph Grishman. 2008. Refining event extraction through cross-document inference. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  17. Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. 2020. BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proceedings of the 58th Annual Meeting of the… find our card
  18. Fayuan Li, Weihua Peng, Yuguang Chen, Quan Wang, Lu Pan, Yajuan Lyu, and Yong Zhu. 2020. Event extraction as multi-turn question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings (EMNLP). find our card
  19. 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 (ACL). find our card
  20. Sha Li, Heng Ji, and Jiawei Han. 2021. Document-level event argument extraction by conditional generation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). find our card
  21. 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 (ACL). find our card
  22. 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). find our card
  23. Ilya Loshchilov and Frank Hutter. 2019. Decoupled weight decay regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. find
  24. Yaojie Lu, Hongyu Lin, Jin Xu, Xianpei Han, Jialong Tang, Annan Li, Le Sun, Meng Liao, and Shaoyi Chen. 2021. Text2event: Controllable sequence-to-structure generation for end-to-end event extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the… find our card
  25. Thien Huu Nguyen, Kyunghyun Cho, and Ralph Grishman. 2016. Joint event extraction via recurrent neural networks. In The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). find our card
  26. Thien Huu Nguyen and Ralph Grishman. 2015. Event detection and domain adaptation with convolutional neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL). find our card
  27. 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, The Thirty-First Innovative Applications of Artificial Intelligence Conference (AAAI). find
  28. Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cícero Nogueira dos Santos, Bing Xiang, and Stefano Soatto. 2021. Structured prediction as translation between augmented natural languages. In 9th International Conference on Learning Representations (ICLR)… find
  29. 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 Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI). find
  30. Shirong Shen, Tongtong Wu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari, and Sheng Bi. 2021. Adaptive knowledge-enhanced bayesian meta-learning for few-shot event detection. In Findings of the Association for Computational Linguistics: ACL/IJCNLP. find
  31. Zhiyi Song, Ann Bies, Stephanie M. Strassel, Tom Riese, Justin Mott, Joe Ellis, Jonathan Wright, Seth Kulick, Neville Ryant, and Xiaoyi Ma. 2015. From light to rich ERE: annotation of entities, relations, and events. In Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreferenc… find our card
  32. Jiao Sun and Nanyun Peng. 2021. Men are elected, women are married: Events gender bias on wikipedia. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL/IJCNLP 2021, (Volume 2: Shor… find
  33. 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
  34. Xiaozhi Wang, Ziqi Wang, Xu Han, Wangyi Jiang, Rong Han, Zhiyuan Liu, Juanzi Li, Peng Li, Yankai Lin, and Jie Zhou. 2020. MAVEN: A massive general domain event detection dataset. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, November 1… find our card
  35. 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
  36. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho… find our card
  37. Bishan Yang and Tom M. Mitchell. 2016. Joint extraction of events and entities within a document context. In The 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). find our card
  38. Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, and Dongsheng Li. 2019a. Exploring pre-trained language models for event extraction and generation. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Lon… find our card
  39. Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, and Dongsheng Li. 2019b. Exploring pre-trained language models for event extraction and generation. In Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL). find our card
  40. Hongming Zhang, Xin Liu, Haojie Pan, Yangqiu Song, and Cane Wing-Ki Leung. 2020. ASER: A large-scale eventuality knowledge graph. In The Web Conference 2020 (WWW). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/hsu-2022-degree-data-efficient-generation-based/