目前大多数事件检测研究都认为句子之间是相互独立的,忽略了句子之间、触发词之间的事件关联。基于此,该文提出了一种基于句子类别信息的事件检测方法。首先通过基于BERT和注意力机制的句子级事件检测模型获取句子类别信息,构建句子之间的事件关联。然后该文通过基于机器阅读理解的事件检测模型融合句子类别信息,并学习句子标签的文本信息。此外,加入对比学习模块,拉近同类别触发词之间的距离,学习触发词之间的事件关联。最终实验表明,该模型在ACE中文和英文数据集上相比基准模型F1值分别获得了1.6%和1.1%的提升。
Abstract
Most of the current event detection researches treat the sentences as independent of each other, ignoring the event correlation between sentences and triggers. In contrast, this paper proposes an event detection method based on the sentence type information. Firstly, we obtain the sentence type information through a sentence-level event detection model based on BERT and attention mechanism, and construct event correlation between sentences. Then, we design an event detection model based on machine reading comprehension to fuse sentence type information and learn the textual information of the sentence label. In addition, a contrastive learning module is added to shorten the trigger distance of the same type and learn the event association between triggers. The experiments in ACE Chinese and English datasets show that the proposed model have improved F1 value by 1.6% and 1.1%, respectively, compared with the benchmark models.
关键词
事件检测 /
句子类别信息 /
对比学习
{{custom_keyword}} /
Key words
event detection /
sentence type information /
contrastive learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] AHN D. The stages of event extraction[C]//Proceedings of the Workshop on Annotating and Reasoning about Time and Events, 2006: 1-8.
[2] JI H,GRISHMAN R. Refining event extraction through cross-document inference[C]//Proceedings of 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2008: 254-262.
[3] HUANG R,RILOFF E. Modeling textual cohesion for event extraction[C]//Proceedings of the 26th AAAI Conference on Artificial Intelligence, 2012: 1664-1669.
[4] LI Q, JI H, HUANG L. Joint event extraction via structured prediction with global features[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 2013: 73-82.
[5] NGUYEN T H, GRISHMAN R. Event detection and domain adaptation with 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, 2015: 365-371.
[6] 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, 2015: 167-176.
[7] NGUYEN T H, CHO K,GRISHMAN R. Joint event extraction via recurrent neural networks[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016: 300-309.
[8] CHEN Z, JI H. Language specific issue and feature exploration in Chinese event extraction[C]//Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2009: 209-212.
[9] NGUYEN T,GRISHMAN R. Graph convolutional networks with argument-aware pooling for event detection[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018: 5900-5907.
[10] LIU X, LUO Z, HUANG H Y. Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 1247-1256.
[11] YAN H, JIN X, MENG X, et al. Event detection with multi-order graph convolution and aggregated attention[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing, 2019: 5766-5770.
[12] LAI V D, NGUYEN T N, NGUYEN T H. Event detection: Gate diversity and syntactic importance scores for graph convolution neural networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 5405-5411.
[13] CUI S, YU B, LIU T, et al. Edge-enhanced graph convolution networks for event detection with syntactic relation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings, 2020: 2329-2339.
[14] LIU A, XU N, LIU H. Self-attention graph residual convolutional networks for event detection with dependency relations[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings, 2021: 302-311.
[15] LIU S, LI Y, ZHANG F, et al. Event detection without triggers[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 735-744.
[16] XU W, ZHANG W, WANG D. Event detection without trigger words on movie scripts[C]//Proceedings of the International Conference on Image, Video Processing and Artificial Intelligence. International Society for Optics and Photonics, 2020, 11584: 115841G.
[17] DEVLIN J, CHANG M W, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171-4186.
[18] WANG X, HAN X, LIU Z, et al. Adversarial training for weakly supervised event detection[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 998-1008.
[19] DU X,CARDIE C. Event extraction by answering (Almost)natural questions[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 671-683.
[20] LIU J, CHEN Y, LIU K, et al. Event extraction as machine reading comprehension[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 1641-1651.
[21] HUANG Y, JIA W. Exploring sentence community for document-level event extraction[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings, 2021: 340-351.
[22] HJELM R D, FEDOROV A, LAVOIE-MARCHILDON S, et al. Learning deep representations by mutual information estimation and maximization[C]//Proceedings of the International Conference on Learning Representations, 2018.
[23] MIYATO T, DAI A M, GOODFELLOW I. Adversarial training methods for semi-supervised text classification[C]//Proceedings of ICLR, 2017.
[24] DING N, LI Z, LIU Z, et al. Event detection with trigger-aware lattice neural network[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 347-356.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61836007,62006167,61806137);江苏高校优势学科建设工程资助项目
{{custom_fund}}
PDF(2132 KB)
