Elamur Research⌕
☰
home / papers / 2022 / Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction

Summary

Event Argument Extraction (EAE) means finding the text spans that fill the roles of a detected event, such as the Seller or Artifact of a sale. Earlier QA-style systems ask about roles one at a time, which is slow. Generation-based systems emit all arguments in sequence and lose accuracy on long-distance and numerous arguments. The authors propose PAIE, which adapts prompt tuning to extraction rather than to classification or generation. For each event type, a single joint prompt lists every role as a slot. A PLM reads the prompt together with the context and turns each slot into a role-specific query, and two span selectors use these queries to pick start and end tokens in the input. All arguments are predicted at once. Training uses a bipartite matching loss that pairs predictions with gold arguments at minimal cost. Because a role can appear in several slots, multiple same-role arguments are handled without threshold tuning. PAIE works at both sentence and document level, runs faster than QA baselines and performs well when training data is scarce.

Key points

  • PAIE was evaluated on three benchmarks: ACE05 (sentence-level), RAMS and WIKIEVENTS (document-level). Average F1 gains were 3.5% for PAIE-base and 2.3% for PAIE-large.
  • The authors compare three prompt variants: manual template, concatenation template and soft prompt. Code is available at github.com/mayubo2333/PAIE.
  • On WIKIEVENTS roles that have several arguments, PAIE beats EEQA-BART in Arg-C F1 by 9.5% for roles with three arguments and by 26.4% for roles with four or more.
  • In few-shot experiments on the document-level datasets, PAIE trained on about 20% of the data matches EEQA-BART, and with about 10% it matches EEQA.
  • Inference is roughly 3–4 times faster than EEQA, measured on a single NVIDIA 1080Ti GPU, because roles are predicted simultaneously.

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.acl-long.466

@inproceedings{ma2022prompt,
  title = {{Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction}},
  author = {Ma, Yubo and Wang, Zehao and Cao, Yixin and Li, Mukai and Chen, Meiqi and Wang, Kun and Shao, Jing},
  booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2022},
  doi = {10.18653/v1/2022.acl-long.466},
  url = {https://doi.org/10.18653/v1/2022.acl-long.466}
}

References

36 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko. 2020. End-to-end object detection with transformers. In Proceedings of ECCV. find our card
  2. 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 our card
  3. Leyang Cui, Yu Wu, Jian Liu, Sen Yang, and Yue Zhang. 2021. Template-based named entity recognition using BART. In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1835–1845, Online. Association for Computational Linguistics. find our card
  4. 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 our card
  5. 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
  6. Harold W Kuhn. 1955. The hungarian method for the assignment problem. Naval research logistics quarterly, 2(1-2):83–97. find
  7. 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
  8. 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 our card
  9. 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 our card
  10. 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, pages 894–908, Online. Association for Computa… find our card
  11. Seth Ebner, Patrick Xia, Ryan Culkin, Kyle Rawlins, and Benjamin Van Durme. 2020. Multi-sentence argument linking. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8057–8077, Online. Association for Computational Linguistics. find our card
  12. Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In 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), pages 4582–… find
  13. Kung-Hsiang Huang and Nanyun Peng. 2021. Document-level event extraction with efficient end-to-end learning of cross-event dependencies. In Proceedings of the Third Workshop on Narrative Understanding, pages 36–47, Virtual. Association for Computational Linguistics. find
  14. 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
  15. 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 our card
  16. 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
  17. Yusheng Huang and Weijia Jia. 2021. Exploring sentence community for document-level event extraction. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 340–351, Punta Cana, Dominican Republic. Association for Computational Linguistics. find
  18. Jian Liu, Yufeng Chen, and Jinan Xu. 2021a. Machine reading comprehension as data augmentation: A case study on implicit event argument extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2716– 2725, Online and Punta Cana, Dominican Republic.… find
  19. Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2021b. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. find our card
  20. Xiao Liu, Kaixuan Ji, Yicheng Fu, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021c. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. ArXiv preprint, abs/2110.07602. find our card
  21. Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2021d. Gpt understands, too. find our card
  22. 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
  23. 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 our card
  24. 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
  25. Guanghui Qin and Jason Eisner. 2021. Learning how to ask: Querying LMs with mixtures of soft prompts. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5203–5212, Online. Association for Computatio… find our card
  26. 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-18), the 30th innovative Applications of Arti… find
  27. Beth M. Sundheim. 1992. Overview of the fourth Message Understanding Evaluation and Conference. In Fourth Message Uunderstanding Conference (MUC-4): Proceedings of a Conference Held in McLean, Virginia, June 16-18, 1992. find
  28. 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
  29. Ziqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin, Lei Hou, Zhiyuan Liu, Peng Li, Juanzi Li, and Jie Zhou. 2021. CLEVE: Contrastive Pre-training for Event Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on N… find
  30. Kaiwen Wei, Xian Sun, Zequn Zhang, Jingyuan Zhang, Guo Zhi, and Li Jin. 2021. Trigger is not sufficient: Exploiting frame-aware knowledge for implicit event argument extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Join… find
  31. 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
  32. Runxin Xu, Tianyu Liu, Lei Li, and Baobao Chang. 2021. Document-level event extraction via heterogeneous graph-based interaction model with a tracker. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Lan… find
  33. Timo Schick and Hinrich Schütze. 2021. Exploiting cloze-questions for few-shot text classification and natural language inference. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 255–269, Online. Association for Compu… find our card
  34. Hang Yang, Yubo Chen, Kang Liu, Yang Xiao, and Jun Zhao. 2018. DCFEE: A document-level Chinese financial event extraction system based on automatically labeled training data. In Proceedings of ACL 2018, System Demonstrations, pages 50–55, Melbourne, Australia. Association for Computational Linguisti… find
  35. Hang Yang, Dianbo Sui, Yubo Chen, Kang Liu, Jun Zhao, and Taifeng Wang. 2021. Document-level event extraction via parallel prediction networks. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language P… find
  36. 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

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ma-2022-prompt-extraction-paie-prompting-argument/