计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (7): 287-295.doi: 10.11896/jsjkx.230700118

• 人工智能 • 上一篇    下一篇

基于联合学习的语言粒度融合的重叠事件抽取方法

闫婧涛1, 李旸2, 王素格1,3, 潘邦泽1   

  1. 1 山西大学计算机与信息技术学院 太原 030006
    2 山西财经大学金融学院 太原 030006
    3 山西大学计算智能与中文信息处理教育部重点实验室 太原 030006
  • 收稿日期:2023-07-17 修回日期:2023-12-09 出版日期:2024-07-15 发布日期:2024-07-10
  • 通讯作者: 李旸(liyangprimrose@163.com)
  • 作者简介:(yanjingtao0731@163.com)
  • 基金资助:
    国家重点研发计划(2022QY0300-01);国家自然科学基金(62106130);山西省高等学校科技创新项目(2021L284)

Overlap Event Extraction Method with Language Granularity Fusion Based on Joint Learning

YAN Jingtao1, LI Yang2, WANG Suge1,3, PAN Bangze1   

  1. 1 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China
    2 School of Finance,Shanxi University of Finance and Economics,Taiyuan 030006,China
    3 Key Laboratory Computational Intelligence and Chinese Information Processing of Ministry of Education,Shanxi University,Taiyuan 030006,China
  • Received:2023-07-17 Revised:2023-12-09 Online:2024-07-15 Published:2024-07-10
  • About author:YAN Jingtao,born in 1999,postgra-duate.Her main research interest is natural language processing.
    LI Yang,born in 1988,Ph.D,associate professor,is a member of CCF(No.33621G).Her main research interests include text sentiment analysis and text mining.
  • Supported by:
    National Key Research and Development Program of China(2022QY0300-01),National Natural Science Foundation of China(62106130) and Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi(2021L284).

PDF (PC)

398

摘要： 事件抽取是一项重要的信息抽取任务,现有的事件抽取方法大多假设一个句子中仅出现一个事件,然而,在真实的场景下,重叠事件是难以避免的。文中提出了一种基于联合学习的语言粒度融合的重叠事件抽取方法。该方法设计了基于token数目逐层递增和逐层递减的策略,对不同语言粒度的片段进行表示,在此基础上,构建了渐进式语言粒度融合的句子表示。通过引入事件信息感知,建立了基于门控机制的语言粒度和事件信息融合的句子表示。最后,通过联合学习词间的片段关系和角色关系,实现对事件触发词、论元、事件类型和论元角色的判别。在FewFC和DuEE1.0-1数据集上进行了实验,所提LGFEE模型在事件类型判别任务上的F1值分别提高了0.8%和0.6%,在触发词识别、论元识别、论元角色分类任务上也获得了较高的召回率和F1值,验证了其有效性。

关键词: 重叠事件抽取, 语言粒度融合, 联合学习, 注意力机制, 门控机制

Abstract: Event extraction is a crucial task in information extraction.The existing event extraction methods generally assume that only one event occurs in a sentence.However,overlapping events are inevitable in real scenarios.Therefore,this paper designs an overlap event extraction method with language granularity fusion based on joint learning.In this method,a strategy of increasing and decreasing token number layer by layer is designed to represent fragments of different language granularity.On this basis,a sentence representation of progressive language granularity fusion is constructed.By introducing event information perception,the sentence representation of language granularity and event information fusion based on gating mechanism is established.Finally,through the joint study of the fragment relationship and role relationship between words,the identification of event triggering words,arguments,event types and argument roles is realized.The experiments conducted on the FewFC and DuEE1.0-1datasets demonstrate that the LGFEE model proposed in this paper achieves an improvement of 0.8% and 0.6% in the F1 score for event type discrimination tasks,respectively.Furthermore,it also exhibits higher recall rates and F1 scores in trigger word recognition,argument recognition,and argument role classification tasks,which verifies the validity of LGFEE model.

Key words: Overlapping event extraction, Language granularity fusion, Joint learning, Attention mechanism, Gating mechanism

中图分类号: 

  • TP391
[1]HUANG K H,YANG M,PENG N.Biomedical event extraction with hierarchical knowledge graphs[C]//Findings of the Association for Computational Linguistics(EMNLP 2020).2020:1277-1285.
[2]YANG H,CHEN Y,LIU K,et al.DCFEE:a document-levelChinese financial event extraction system based on automatically labeled training data[C]//Proceedings of the 56th Annual Mee-ting of the Association for Computational Linguistics(ACL 2018).2018:50-55.
[3]HALTERMAN A,KEITH K A,SARWAR S M,et al.Corpus-level evaluation for event QA:the IndiaPoliceEvents corpus cove-ring the 2002 Gujarat violence[C]//Findings of the Association for Computational Linguistics(ACL-IJCNLP 2021).2021:4240-4253.
[4]SHENG J,GUO S,YU B,et al.CaSEE:a joint learning framework with cascade decoding for overlapping event extraction[C]//Findings of the Association for Computational Linguistics:ACL-IJCNLP.2021:164-174.
[5]LIU X,LUO Z,HUANG H.Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:1247-1256.
[6]NGUYEN T H,CHO K,GRISHMAN R.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.
[7]CAO H,LI J,SU F,et al.OneEE:a one-stage framework for fast overlapping and nested event extraction[C]//Proceedings of the 29th International Conference on Computational Linguistics.2022:1953-1964.
[8]LIU W,MA Y W,PENG Y,et al.Chinese event extractionmethod based on graph attention and table pointer network [J].Pattern Recognition and Artificial Intelligence,2023,36(5):459-470.
[9]XIN M M,MA L,HU B F.Research on text classification fusing multi-granularity information [J].Computer Engineering and Applications,2023,59(9):104-111.
[10]LI Y,CUI L,YIN Y,et al.Multi-granularity optimization for non-autoregressive translation[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Proces-sing.2022:5073-5084.
[11]DEVLIN J,CHANG M W,LEE K,et al.Bert:pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[12]LI Q,LI J,SHENG J,et al.A survey on deep learning event extraction:approaches and applications[J/OL].https://doi.org/10.1109/TNNLS.2022.3213168.
[13]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 Computa-tional Linguistics and the 7th International Joint Conference on Natural Language Processing.2015:167-176.
[14]YANG S,FENG D,QIAO L,et al.Exploring pre-trained language models for event extraction and generation[C]//Procee-dings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:5284-5294.
[15]XU J,XU W,SUN M,et al.Extracting trigger-sharing events via an event matrix[C]//Findings of the Association for Computational Linguistics(EMNLP 2022).2022:1189-1201.
[16]LI Q,PENG H,LI J,et al.Reinforcement learning-baseddialogue guided event extraction to exploit argument relations[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2022,30:520-533.
[17]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[18]SUN Y,CHENG C,ZHANG Y,et al.Circle loss:a unified perspective of pair similarity optimization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:6398-6407.
[19]ZHOU Y,CHEN Y,ZHAO J,et al.What the role is vs.what plays the role:semi-supervised event argument extraction via dual question answering[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.2021:14638-14646.
[20]LI X,LI F,PAN L,et al.DuEE:a large-scale dataset forchinese event extraction in real-world scenarios[C]//Natural Language Processing and Chinese Computing:9th CCF International Conference(NLPCC 2020).2020:534-545.
[21]DU X,CARDIE C.Document-level event role filler extractionusing multi-granularity contextualized encoding[C]//Procee-dings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:8010-8020.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发