事件检测任务旨在从非结构化的文本中自动识别并分类事件触发词。挖掘和表示实体的属性特征(即实体画像)有助于事件检测,其基本原理在于“实体本身的属性往往暗示了其参与的事件类型”(例如,“警察”往往参与“Arrest-Jail”类的事件)。现有研究已利用编码信息实现实体表示,并借此优化事件检测模型。然而,其表示学习过程仅仅纳入局部的句子级语境信息,使得实体画像的信息覆盖率偏低。为此,该文提出基于全局信息和实体交互信息的画像增强方法,其借助图注意力神经网络,不仅在文档级的语境范围内捕捉实体的高注意力背景信息,也同时纳入了局部相关实体的交互信息。特别地,该文开发了基于共现图的注意力遮蔽模型,用于降低噪声信息对实体表示学习过程的干扰。在此基础上,该文联合上述实体画像增强网络、BERT语义编码网络和GAT聚合网络,形成了总体的事件检测模型。该文在通用数据集ACE 2005上进行实验,结果表明实体画像增强方法能够进一步优化事件检测的性能,在触发词分类任务上的F1值达到76.2%,较基线模型提升了2.2%。
Abstract
Event detection aims to automatically identify and classify event triggers from unstructured texts. Entity representation(or entity profiling)is deemed to be positive to event detection based on the hypothesis that “the features of entities often implies the type of events they participate in” (for example, “police” often participate in “Arrest-Jail” type of events). In this paper, we propose an entity representation enhancement method based on the document-level context and entities interaction. We use the graph attention neural network to capture the document-level information of entities on the background of high attention network, and take into account the local interactive information of other related entities. In particular, an attention mask model based on the entity co-occurrence graph is developed to reduce the noise information. We finally combine the entity representation enhancement network, BERT semantic encoding network, and GAT aggregation network to form the overall event detection model. Experiments on ACE2005 demonstrate the proposed method achieves 76.2% F1 score in trigger classification task, outperforming the baseline model by 2.2%.
关键词
事件检测 /
实体特征 /
全局语义 /
图注意力网络
{{custom_keyword}} /
Key words
event detection /
entity features /
global semantics /
graph attention network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 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.
[2] Christopher W, Stephanie S, Julie M, et al. ACE 2005 multilingual training corpus[C]//Proceedings of the Linguistic Data Consortium, Philadelphia, 2006:45-57.
[3] Devlin J, Chang M W, Lee K, et al. BERT: Pretraining 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.
[4] Liu Y, Ott M, Goyal N, et al. Roberta: A robustly optimized BERT pretraining approach[J]. arXiv preprint arXiv:1907.11692, 2019.
[5] Hong Y, Zhang J, Ma B, et al. Using cross-entity inference to improve event extraction[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011: 1127-1136.
[6] Zhao Y, Jin X, Wang Y, et al. Document embedding enhanced event detection with hierarchical and supervised attention[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 414-419.
[7] Liu S, Chen Y, Liu K, et al. Exploiting argument information to improve event detection via supervised attention mechanisms[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1789-1798.
[8] Nguyen T H, Grishman R. Modeling skip-grams for event detection with convolutional neural networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 886-891.
[9] 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.
[10] Ji Y, Lin Y, Gao J, et al. Exploiting the entity type sequence to benefit event detection[C]//Proceedings of the 23rd Conference on Computational Natural Language Learning, 2019: 613-623.
[11] Liao S, Grishman R. Using document level cross-event inference to improve event extraction[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, 2010: 789-797.
[12] Grishman R. The impact of task and corpus on event extraction systems[C]//Proceedings of the 7th International Conference on Language Resources and Evaluation, 2010.
[13] Liu S, Chen Y, He S, et al. Leveraging framenet to improve automatic event detection[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 2134-2143.
[14] 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 Conferences on Artificial Intelligence, 2015: 365-371.
[15] Nguyen T H, Cao K, Grishman R. Joint event extraction via recurrent neural networks[C]//Proceedings of the Conference of Annual Conference of the North American Chapter of the Association for Computational Linguistics and Human Language Technologies, 2016: 300-309.
[16] Liu S, Chen Y, Liu K, et al. Exploiting argument information to improve event detection via supervised attention mechanisms[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 1789-1798.
[17] Chen Y, Yang H, Liu K, et al. Collective event detection via a hierarchical and bias tagging networks with gated multi-level attention mechanisms[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 1267-1276.
[18] Nguyen T H, Grishman R. Graph convolutional networks with argument-aware pooling for event detection[C]//Proceedings of the 32th Association for the Advancement of Artificial Intelligence conference on artificial intelligence, 2018.
[19] Xiao L, Luo Z, Huang H. Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018.
[20] Veyseh A P B, Nguyen T H, Dou D. Graph based neural networks for event factuality prediction using syntactic and semantic structures[J]. arXiv preprint arXiv:1907. 03227, 2019.
[21] Cui S, Yu B, Liu T, et al. Edge-enhanced graph convolution networks for event detection with syntactic relation[J]. arXiv preprint arXiv:2002.10757, 2020.
[22] Lai V D, Nguyen T N. Event detection: Gate diversity and syntactic importance scoresfor graph convolution neural networks[J]. arXiv preprint arXiv:2010. 14123, 2020.
[23] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv:1609. 02907, 2016.
[24] Veliǒkovi＇c P, Cucurull G, Casanova A, et al. Graph attentions network[C]//Proceedings of the International Conference on Learning Representations, 2018: 1-12.
[25] Wang T, Wan X. T-CVAE: Transformer-based conditioned variational autoencoder for story completion[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, 2019: 5233-5239.
[26] Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models[C]//Proceedings of the 30th International Conference on Machine Learning, 2013, 30(1): 3.
[27] 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.
[28] Yang B, Mitchell T. Joint extraction of events and entities within a document context[J].arXiv preprint arXiv:1609. 03632, 2016.
[29] 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 9th International Joint Conference on Natural Language Processing, 2019: 5766-5770.
[30] Liu J, Chen Y, Liu K, et al. How does context matter? on the robustness of event detection with context-selective mask generalization[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing: Findings, 2020: 2523-2532.
[31] Dror R, Baumer G, Shlomov S, et al. The hitchhiker's guide to testing statistical significance in natural language processing[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1383-1392.
[32] Johnson D H. The insignificance of statistical significance testing[J]. The Journal of Wildlife Management, 1999: 763-772.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
科技部专项课题(2020YFB1313601);国家自然科学基金(62076174);江苏高校优势学科建设工程资助项目
{{custom_fund}}
PDF(5205 KB)
