一个实体关系与事件抽取的通用模型

doi:10.19678/j.issn.1000-3428.0063662

摘要/Abstract

摘要： 信息提取的目的是从自然语言文件中找到具体信息，现有研究在信息抽取的实体关系和事件抽取任务中仅解决事件论元重叠和实体关系重叠的问题，未考虑两个任务共有的角色重叠问题，导致抽取结果准确率降低。提出一个两阶段的通用模型用于完成实体关系抽取和事件抽取子任务。基于预训练语言模型RoBERTa的共享特征表示，分别对实体关系/事件类型和实体关系/事件论元进行预测。将传统抽取触发词任务转化为多标签抽取事件类型任务，利用多尺度神经网络进一步提取文本特征。在此基础上，通过抽取文本相关类型的事件论元，根据论元角色的重要性对损失函数重新加权，解决数据不平衡、实体关系抽取和事件抽取中共同存在论元角色重叠的问题。在千言数据集中事件抽取和关系抽取任务测试集上的实验验证了该模型的有效性，结果表明，该模型的F1值分别为83.1%和75.3%。

关键词: 事件抽取, 实体关系抽取, 角色重叠, RoBERTa模型, 多标签分类

Abstract: The purpose of information extraction is to find specific information from natural language files.Existing research has only focused on solving the problem of event argument overlap and entity relationship overlap in the entity relationship and event extraction tasks of information extraction;it has not considered the problem of roles overlap shared by the two tasks, which leads to a reduction in the accuracy of extraction results.A general two-phase model is proposed to complete the sub-tasks of entity relationship extraction and event extraction.Based on the shared feature representation of the pre-training language model RoBERTa, the entity relationship/event type and entity relationship/event argument are predicted.The traditional task of extracting trigger words is transformed into a task of extracting event types from multi-label, and the text features are further extracted using multi-scale neural networks.On this basis, the loss function is reweighted according to the importance of argument roles by extracting event arguments of text-related types to solve the problem of data imbalance and overlapping of argument roles in entity relationship extraction and event extraction.Experiments on event extraction task testset and relation extraction task testset in Luge dataset verify the effectiveness of the proposed model.The experimental results show that the F1 values of the proposed model on these two test sets are 83.1% and 75.3%, respectively.

Key words: event extraction, entity relationship extraction, roles overlap, RoBERTa model, multi-label classification

中图分类号:

TP391.1

杨红菊, 靳新宇. 一个实体关系与事件抽取的通用模型[J]. 计算机工程, 2023, 49(2): 143-149.

YANG Hongju, JIN Xinyu. A General Model for Entity Relationship and Event Extraction[J]. Computer Engineering, 2023, 49(2): 143-149.

http://www.ecice06.com/CN/Y2023/V49/I2/143

图/表 6

20230216180947

20230216180950

20230216181019

20230216181022

20230216181025

20230216181028

参考文献

[1] CHEN Z, JI H.Language specific issue and feature eploration in Chinese event extraction[C]//Proceedings of Conference on Human Language Technologies.Washington D.C., USA:IEEE Press, 2009:209-212.
[2] 贺瑞芳, 段绍杨.基于多任务学习的中文事件抽取联合模型[J].软件学报, 2019, 30(4):1015-1030. HE R F, DUAN S Y.Joint Chinese event extraction based multi-task learning[J].Journal of Software, 2019, 30(4):1015-1030.(in Chinese)
[3] LI X Y, LI F Y, PAN L, et al.DuEE:a large-scale dataset for Chinese event extraction in real-world scenarios[C]//Proceedings of International Conference on Natural Language Processing and Chinese Computing.Berlin, Germany:Springer, 2020:534-545.
[4] LI S J, HE W, SHI Y B, et al.DuIE:a large-scale Chinese dataset for information extraction[C]//Proceedings of International Conference on Natural Language Processing and Chinese Computing.Berlin, Germany:Springer, 2019:791-800.
[5] RILOFF E.Automatically constructing a dictionary for information extraction tasks[C]//Proceedings of the 11th National Conference on Artificial Intelligence.New York, USA:ACM Press, 1993:811-816.
[6] KIM J T, MOLDOVAN D I.Acquisition of linguistic patterns for knowledge-based information extraction[J].IEEE Transactions on Knowledge and Data Engineering, 1995, 7(5):713-724.
[7] YU S H, BAI S H, WU P H.Description of the Kent Ridge digital labs system used for MUC-7[C]//Proceedings of the 7th Message Understanding Conference.Fairfax, Virginia, USA:[s.n.], 1998:1-10.
[8] ZENG D, LIU K, LAI S, et al.Relation classification via convolutional deep neural nework[C]//Proceedings of the 25th International Conference on Computational Linguistics.Dublin, Irelond:[s.n.], 2014:2335-2344.
[9] CHEN Y B, XU L H, 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.Stroudsburg, USA:Association for Computational Linguistics, 2015:167-176.
[10] SOCHER R, HUVAL B, MANNING C D, et al.Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.New York, USA:ACM Press, 2012:1201-1211.
[11] FENG X C, HUANG L F, TANG D Y, et al.A language-independent neural network for event detection[EB/OL].[2021-11-27].https://aclanthology.org/P16-2011.pdf.
[12] NGUYEN T H, CHO K, GRISHMAN R.Joint event extraction via recurrent neural networks[C]//Proceedings of Conference on the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg, USA:Association for Computational Linguistics, 2016:300-309.
[13] KATIYAR A, CARDIE C.Going out on a limb:joint extraction of entity mentions and relations without dependency trees[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Stroudsburg, USA:Association for Computational Linguistics, 2017:917-928.
[14] LIU X, LUO Z C, HUANG H Y.Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2018:1247-1256.
[15] 武国亮, 徐继宁.基于命名实体识别任务反馈增强的中文突发事件抽取方法[J].计算机应用, 2021, 41(7):1891-1896. WU G L, XU J N.Chinese emergency event extraction method based on named entity recognition task feedback enhancement[J].Journal of Computer Applications, 2021, 41(7):1891-1896.(in Chinese)
[16] 唐朝, 诺明花, 胡岩.ResNet结合BiGRU的关系抽取混合模型[J].中文信息学报, 2020, 34(2):38-45. TANG C, NUO M H, HU Y.A hybrid model for relation extraction via ResNet & BiGRU[J].Journal of Chinese Information Processing, 2020, 34(2):38-45.(in Chinese)
[17] YANG S, FENG D W, QIAO L B, et al.Exploring pre-trained language models for event extraction and generation[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Stroudsburg, USA:Association for Computational Linguistics, 2019:5284-5294.
[18] ZHAO T Y, YAN Z, CAO Y B, et al.Asking effective and diverse questions:a machine reading comprehension based framework for joint entity-relation extraction[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence.Yokohama, Japan:[s.n.], 2021:3948-3954.
[19] DU X Y, CARDIE C.Event extraction by answering (almost) natural questions[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2020:671-683.
[20] ZHONG Z X, CHEN D Q.A frustratingly easy approach for entity and relation extraction[EB/OL].[2021-11-27].https://arxiv.org/abs/2010.12812.
[21] LIU J, CHEN Y B, LIU K, et al.Event extraction as machine reading comprehension[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg, USA:Association for Computational Linguistics, 2020:1641-1651.
[22] XU N, XIE H H, ZHAO D Y.A novel joint framework for multiple Chinese events extraction[C]//Proceedings of China National Conference on Chinese Computational Linguistics.Berlin, Germany:Springer, 2020:174-183.
[23] 王炳乾, 宿绍勋, 梁天新.基于BERT的多层标签指针网络事件抽取模型[J].中文信息学报, 2021, 35(7):81-88. WANG B Q, SU S X, LIANG T X.BERT based multi-layer label pointer network for event extraction[J].Journal of Chinese Information Processing, 2021, 35(7):81-88.(in Chinese)
[24] SUI D B, CHEN Y B, LIU K, et al.Joint entity and relation extraction with set prediction networks[EB/OL].[2021-11-27].https://arxiv.org/abs/2011.01675.
[25] LIU Y H, OTT M, GOYAL N, et al.RoBERTa:a robustly optimized BERT pretraining approach[EB/OL].[2021-11-27].https://arxiv.org/abs/1907.11692.

选择文件类型/文献管理软件名称

选择包含的内容