模式识别与人工智能
Monday, Apr. 7, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2023, Vol. 36 Issue (5): 459-470    DOI: 10.16451/j.cnki.issn1003-6059.202305006
Researches and Applications Current Issue| Next Issue| Archive| Adv Search |
Chinese Event Extraction Method Based on Graph Attention and Table Pointer Network
LIU Wei1,2, MA Yawei1, PENG Yan3, LI Weimin1
1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444;
2. Shanghai Artificial Intelligence Laboratory, Shanghai 200232;
3. Institute of Artificial Intelligence, Shanghai University, Shanghai 200444

Download: PDF (823 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The existing Chinese event extraction methods suffer from inadequate modeling of dependencies between an event trigger word and all its corresponding arguments, which results in weakened information interaction within an event and poor performance in argument extraction, especially when there is argument role overlap. To address this issue, a Chinese event extraction method based on graph attention and table pointer network(ATCEE) is proposed in this paper. Firstly,pre-trained character vectors and part-of-speech tagging vectors are fused as feature inputs. Then, the enhanced feature of the event text is obtained by a bidirectional long short-term memory network. Next, a character-level dependency syntax graph is constructed and introduced into multi-layer graph attention network to capture long-range dependencies among constituents of the event text. Subsequently, dependencies between an event trigger word and all its corresponding arguments are further enhanced via a table filling strategy. Finally, the learned table feature is input into a fully connected layer and table pointer network layer for joint extraction of trigger words and arguments. Consequently, long argument entities can be identified better by decoding argument boundaries with a table pointer network. Experimental results indicate that ATCEE method significantly outperforms previous event extraction methods on Chinese benchmark datasets, ACE2005 and DuEE1.0. In addition, the overlap problem of the event argument role is solved by introducing character-level dependency feature and table filling strategy to some extent. The source code of ATCEE can be found at the following website: https://github.com/event6/ATCEE.
Key wordsChinese Event Extraction      Argument Role Overlap      Graph Attention Network      Table Fil-ling      Table Pointer Network     
Received: 12 December 2022     
ZTFLH: TP391  
Fund:Major Program of National Natural Science Foundation of China(No.61991410), Program of Pujiang National Laboratory(No.P22KN00391)
Corresponding Authors: LIU Wei, Ph.D., associate professor. His research interests include natural language processing, knowledge representation and reasoning, event ontology and knowledge graph.   
About author:: MA Yawei, master student. His research interests include event extraction and natural language processing.PENG Yan, Ph.D., professor. Her research interests include modeling and control of unmanned surface vehicles, field robotics, and locomotion systems.LI Weimin, Ph.D., professor. His research interests include data intelligence, bioinformation, smart medical and social network.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
LIU Wei
MA Yawei
PENG Yan
LI Weimin
Cite this article:   
LIU Wei,MA Yawei,PENG Yan等. Chinese Event Extraction Method Based on Graph Attention and Table Pointer Network[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(5): 459-470.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202305006      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2023/V36/I5/459
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn