门控机制融合多种特征的中文事件共指消解

doi:10.11896/jsjkx.220700146

计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 291-297.doi: 10.11896/jsjkx.220700146

门控机制融合多种特征的中文事件共指消解

环志刚^1,2, 蒋国权², 张玉健¹, 刘浏^2,3, 刘姗姗²

1 东南大学网络空间安全学院南京 211189
2 国防科技大学第六十三研究所南京 210007
3 宿迁学院信息工程学院江苏宿迁 223800

收稿日期:2022-07-14 修回日期:2022-11-04 出版日期:2023-03-15 发布日期:2023-03-15
通讯作者: 蒋国权(jianggq2001@163.com)
作者简介:(zhiganghuan@seu.edu.cn)
基金资助:
中国博士后科学基金面上资助(2021MD703983);国防科技大学校科研计划项目(ZK20-46)

Employing Gated Mechanism to Incorporate Multi-features into Chinese Event Coreference Resolution

HUAN Zhigang^1,2, JIANG Guoquan², ZHANG Yujian¹, LIU Liu^2,3, LIU Shanshan²

1 School of Cyber Science and Engineering,Southeast University,Nanjing 211189,China
2 The Sixty-third Research Institute,National University of Defense Technology,Nanjing 210007,China
3 School of Information Engineering,Suqian University,Suqian,Jiangsu,223800,China

Received:2022-07-14 Revised:2022-11-04 Online:2023-03-15 Published:2023-03-15
About author:HUAN Zhigang,born in 1997,postgra-duate,is a student member of China Computer Federation.His main research interests include knowledge graph and natural language processing.
JIANG Guoquan,born in 1978,associate research fellow,master,is a member of China Computer Federation.His main research interests include equipment data engineering and knowledge graph.
Supported by:
General Support from China Postdoctoral Science Foundation(2021MD703983) and Scientific Research Program of National University of Defense Technology(ZK20-46).

摘要/Abstract

摘要： 事件共指消解是很多自然语言处理任务的基础,旨在识别文本中指代相同真实事件的事件提及。由于中文语法相比英文更复杂,捕获英文文本特征的方法在中文事件共指消解中效果并不明显。为解决文档内中文事件共指,提出了一种门控机制神经网络(Gated Mechanism Neural Network,GMNN)。针对中文具有主语省略、结构松散等特点,引入事件基本属性作为符号特征。在此基础上,提出了一种新的门控去噪机制,对符号特征向量进行微调,过滤符号特征中的噪声,提取在特定上下文语境中的有用信息,进而提高共指事件的识别率。在ACE2005中文数据集上进行了实验,结果表明,GMNN的AVG分数提升了2.66,有效地提高了中文事件共指消解的效果。

关键词: 中文事件共指消解, 门控机制, 神经网络, 预训练语言模型, 符号特征

Abstract: Event coreference resolution is the basis of many natural language processing tasks,aiming to identify event mentions in text that refer to the same real event.Since Chinese grammar is much more complex than English,the method of capturing English text features is not effective in Chinese event corefe-rence resolution.To solve the within-document Chinese event corefe-rence,a gated mechanism neural network(GMNN) is proposed.In view of Chinese characteristics with subject omission and loose structure,event attributes are introduced as symbolic features.On this basis,a novel gated mechanism is proposed,which fine-tunes the symbolic feature vector,filters the noise in the symbolic features,extracts useful information in a specific context,and improves the coreference events recognition rate.Experimental results on the ACE2005 Chinese dataset show that the perfor-mance of GMNN improves by 2.66,which effectively improves the effect of Chinese event coreference resolution.

Key words: Chinese event coreference resolution, Gated mechanism, Neural network, Pre-trained language models, Symbolic features

中图分类号:

TP391

环志刚, 蒋国权, 张玉健, 刘浏, 刘姗姗. 门控机制融合多种特征的中文事件共指消解[J]. 计算机科学, 2023, 50(3): 291-297. https://doi.org/10.11896/jsjkx.220700146

HUAN Zhigang, JIANG Guoquan, ZHANG Yujian, LIU Liu, LIU Shanshan. Employing Gated Mechanism to Incorporate Multi-features into Chinese Event Coreference Resolution[J]. Computer Science, 2023, 50(3): 291-297. https://doi.org/10.11896/jsjkx.220700146

参考文献

[1]LU J,NG V.Event coreference resolution:a survey of two decades of research[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence.Amsterdam:Elsevier,2018:5479-5486.
[2]MOHAMMED M,MARWA A.Efficient topic detection system for online arabic news [J].International Journal of Computer Applications,2018,180(12):7-12.
[3]CHENG L,GAO H K,WANG H B.A news event extractionmethod in Chinese and Thai languages based on dependency tree elements combined with rules [J].Software Guide,2018,17(7):49-56,63.
[4]WU M Z,MOOSAVI M S,ROTH D,et al.Coreference reaso-ning in machine reading comprehension[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2021:5768-5781.
[5]TENG J Y,LI P F,ZHU Q M.Global inference for co-reference resolution between Chinese events [J].Acta Scientiarum Naturalium Universitatis Pekinensis,2016,52(1):97-103.
[6]CHEN Z,JI H.Graph-based event coreference resolution[C]//Proceedings of the 2009 Workshop on Graph-based Methods for Natural Language Processing.Stroudsburg:ACL,2009:54-57.
[7]CHENG H Y,LI P F,ZHU Q M.Employing gated attention and multi-similarities to resolve document-level Chinese event coreference[C]//International Conference on Asian Language Processing.Piscataway.NJ:IEEE,2019:296-301.
[8]HUAN M,CHEN H Y,LI P F.Resolving Chinese event core-ference via structured representation [J].Journal of Chinese Information Processing,2019,33(12):19-27.
[9]LAI T M,JI H,BUI T,et al.A context-dependent gated module for incorporating symbolic semantics into event coreference resolution[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg,PA:ACL,2021:3491-3499.
[10]LEE K,HE L H,LEWIS M,et al.End-to-end neural coreference resolution[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2017:188-197.
[11] WEI P,CHAO W H,LUO Z C,et al.Selective expression approach based on event trigger for event coreference resolution on Twitter [J].Computer Science,2018,45(12):130-136.
[12] JOSHI M,CHEN D Q,LIU Y H,et al.BERT for coreference resolution:baselines and analysis[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Proces-singand the 9th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2019:5803-5808.
[13]VILAIN M B,BURGER J D,ABERDEEN J S,et al.A model-theoretic coreference scoring scheme[C]//Proceedings of the 6th Conference on Message Understanding.Stroudsburg:ACL,1995:45-52.
[14] BAGGA A,BALDWIN B.Algorithms for scoring coreferencechains[C]//The First Conference Language Resources and Evaluation Coreference.ELRA,1998:563-566.
[15]LUO X Q.On coreference resolution performance metrics[C]//Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2005:25-32.
[16]RECASENS M,HOVY E H.BLANC:implementing the rand index for coreference evaluation [J].Natural Language Engineering,2011,17(4):485-510.

相关文章 15

[1]	李帅, 徐彬, 韩祎珂, 廖同鑫. SS-GCN:情感增强和句法增强的方面级情感分析模型 SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement 计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[2]	陈富强, 寇嘉敏, 苏利敏, 李克. 基于图神经网络的多信息优化实体对齐模型 Multi-information Optimized Entity Alignment Model Based on Graph Neural Network 计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[3]	于健, 赵满坤, 高洁, 王聪源, 李亚蓉, 张文彬. 基于高阶和时序特征的图神经网络社会化推荐算法研究 Study on Graph Neural Networks Social Recommendation Based on High-order and Temporal Features 计算机科学, 2023, 50(3): 49-64. https://doi.org/10.11896/jsjkx.220700108
[4]	李志飞, 赵月, 张龑. 基于表示学习的知识图谱推理研究综述 Survey of Knowledge Graph Reasoning Based on Representation Learning 计算机科学, 2023, 50(3): 94-113. https://doi.org/10.11896/jsjkx.220900136
[5]	饶丹, 时宏伟. 基于深度聚类的航空交通流识别与异常检测研究 Study on Air Traffic Flow Recognition and Anomaly Detection Based on Deep Clustering 计算机科学, 2023, 50(3): 121-128. https://doi.org/10.11896/jsjkx.220100086
[6]	王晓飞, 樊学强, 李章维. 基于迁移学习和多视图特征融合提高RNA碱基相互作用预测 Improving RNA Base Interactions Prediction Based on Transfer Learning and Multi-view Feature Fusion 计算机科学, 2023, 50(3): 164-172. https://doi.org/10.11896/jsjkx.211200186
[7]	梅鹏程, 杨吉斌, 张强, 黄翔. 一种基于三维卷积的声学事件联合估计方法 Sound Event Joint Estimation Method Based on Three-dimension Convolution 计算机科学, 2023, 50(3): 191-198. https://doi.org/10.11896/jsjkx.220500259
[8]	胡中源, 薛羽, 查加杰. 演化循环神经网络研究综述 Survey on Evolutionary Recurrent Neural Networks 计算机科学, 2023, 50(3): 254-265. https://doi.org/10.11896/jsjkx.220600007
[9]	冯程程, 刘派, 姜琳颖, 梅笑寒, 郭贵冰. 文档增强型知识库问答 Document-enhanced Question Answering over Knowledge-Bases 计算机科学, 2023, 50(3): 266-275. https://doi.org/10.11896/jsjkx.220300022
[10]	李海涛, 王瑞敏, 董卫宇, 蒋烈辉. 一种基于GRU的半监督网络流量异常检测方法 Semi-supervised Network Traffic Anomaly Detection Method Based on GRU 计算机科学, 2023, 50(3): 380-390. https://doi.org/10.11896/jsjkx.220100032
[11]	王祥炜, 韩锐, 刘驰. 基于层级化数据记忆池的边缘侧半监督持续学习方法 Hierarchical Memory Pool Based Edge Semi-supervised Continual Learning Method 计算机科学, 2023, 50(2): 23-31. https://doi.org/10.11896/jsjkx.221100133
[12]	章琪, 于双元, 尹鸿峰, 徐保民. 基于图注意力的神经协同过滤社会推荐算法 Neural Collaborative Filtering for Social Recommendation Algorithm Based on Graph Attention 计算机科学, 2023, 50(2): 115-122. https://doi.org/10.11896/jsjkx.211200019
[13]	魏琦, 赵娟. 红外和可见光图像融合算法的研究进展 Research Progress of Infrared and Visible Image Fusion Algorithms 计算机科学, 2023, 50(2): 190-200. https://doi.org/10.11896/jsjkx.220100074
[14]	曹金娟, 钱忠, 李培峰. 基于联合模型的端到端事件可信度识别 End-to-End Event Factuality Identification with Joint Model 计算机科学, 2023, 50(2): 292-299. https://doi.org/10.11896/jsjkx.211200108
[15]	郝敬宇, 文静轩, 刘华锋, 景丽萍, 于剑. 结合全局信息的深度图解耦协同过滤 Deep Disentangled Collaborative Filtering with Graph Global Information 计算机科学, 2023, 50(1): 41-51. https://doi.org/10.11896/jsjkx.220900255

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

门控机制融合多种特征的中文事件共指消解

Employing Gated Mechanism to Incorporate Multi-features into Chinese Event Coreference Resolution

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0