事件抽取(event extraction, EE)是指从自然语言文本中抽取事件并识别事件类型和事件元素的技术,是智能风控、智能投研、舆情监测等人工智能应用的重要技术基础。该文提出一种端到端的多标签指针网络事件抽取方法,并将事件检测任务融入到事件元素识别任务中,达到同时抽取事件元素及事件类型的目的。该方法避免了传统管道式方法存在的错误级联和任务割裂问题,同时也解决了事件抽取中存在的角色重叠和元素重叠问题。该文提出的事件抽取方法在2020语言与智能技术竞赛——事件抽取任务测试集上中取得85.9%的F1值。
Abstract
Event extraction (EE) refers to the technology of extracting events from natural language texts and identifying event types and event elements. This paper proposes an end-to-end multi-label pointer network for event extraction, in which the event detection task is integrated into the event element recognition task to extract event elements and event types at the same time. This method avoids the problem of wrong cascade and task separation in traditional pipeline methods, and alleviates the problem of role overlapping and element overlapping in event extraction. The proposed method achieves 85.9% F1 score on the test set in 2020 Language and Intelligence Challenge Event Extraction task.
关键词
事件抽取 /
指针网络 /
BERT /
角色重叠 /
元素重叠
{{custom_keyword}} /
Key words
event extraction /
pointer net /
BERT /
roles overlap /
argument overlap
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] David A. The stages of event extraction[C]//Proceedings of the Workshop on Annotating and Reasoning about Time and Events. Association for Computational Linguistics, USA, 2006:1-8.
[2] 赵妍妍, 秦兵, 车万翔,等. 中文信息抽取技术研究[J]. 中文信息学报, 2008, 22(1): 3-8.
[3] Chen Y, Xu L, Liu K, et al. Event extraction via dynamic multi-pooling convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, 2015:167-176.
[4] Yang S, Feng D, Qiao L, et al. Exploring pre-trained language models for event extraction and generation[C]//Proceedings of the ACL, Florence, Italy: Association for Computational Linguistics, 2019: 5284-5294.
[5] Nguyen T H, Cho K, Grishman R, et al. Joint event extraction via recurrent neural networks[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational linguistics: Human Language Technologies, 2016:300-309.
[6] Sha L, Qian F, Chang B, et al. Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018:5916-5923.
[7] Liu S L, Li Yang, Zhang F, et al. Event detection without triggers[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis, Minnesota: Association for Computational Linguistics, 2019: 735-744.
[8] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805,2018.
[9] Liu Y, Ott M, Goyal N, et al. RoBERTa: A robustly optimized BERT pretraining approach[J]. arXiv preprint arXiv:1907.11692, 2019.
[10] Liu X, Luo Z C, Huang H Y. Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium: Association for Computational Linguistics, 2018: 1247-1256.
[11] He R F, Duan S Y. Joint Chinese event extraction based multi-task learning[J]. Journal of Software, 2019, 30(4): 1015-1030.
[12] 仲伟峰,杨航,陈玉博,等. 基于联合标注和全局推理的篇章级事件抽取[J]. 中文信息学报, 2019, 33(9): 88-95,106.
[13] Goodfellow I, Shlens J, Szegedy C. Explaining and harnessing adversarial examples[J]. arXiv preprint arXiv:1412.6572, 2014.
[14] Madry A, Makelov A, Schmidt L, et al. Towards deep learning models resistant to adversarial attacks[J]. arXiv preprint arXiv:1706.06083, 2017.
[15] Miyato T, Andrew D, Goodfellow, I. Adversarial training methods for semi-supervised text classification[J]. arXiv preprint arXiv:1605.07725, 2016.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2182 KB)
