Joint Entity-Relation Extraction via Improved Graph Attention Networks

被引:8
|
作者
Lai, Qinghan [1 ]
Zhou, Zihan [1 ]
Liu, Song [1 ]
机构
[1] Qilu Univ Technol, Shandong Acad Sci, Sch Comp Sci & Technol, Jinan 250353, Peoples R China
来源
SYMMETRY-BASEL | 2020年 / 12卷 / 10期
关键词
named entity recognition; relation extraction; graph attention network; adversarial training;
D O I
10.3390/sym12101746
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Joint named entity recognition and relation extraction is an essential natural language processing task that aims to identify entities and extract the corresponding relations in an end-to-end manner. At present, compared with the named entity recognition task, the relation extraction task performs poorly on complex text. To solve this problem, we proposed a novel joint model named extracting Entity-Relations viaImproved Graph Attention networks (ERIGAT), which enhances the ability of the relation extraction task. In our proposed model, we introduced the graph attention network to extract entities and relations after graph embedding based on constructing symmetry relations. To mitigate the over-smoothing problem of graph convolutional networks, inspired by matrix factorization, we improved the graph attention network by designing a new multi-head attention mechanism and sharing attention parameters. To enhance the model robustness, we adopted the adversarial training to generate adversarial samples for training by adding tiny perturbations. Comparing with typical baseline models, we comprehensively evaluated our model by conducting experiments on an open domain dataset (CoNLL04) and a medical domain dataset (ADE). The experimental results demonstrate the effectiveness of ERIGAT in extracting entity and relation information.
引用
收藏
页码:1 / 17
页数:17
相关论文
共 50 条
  • [1] Joint Extraction of Entities and Relations via Entity and Relation Heterogeneous Graph Attention Networks
    Jiang, Bo
    Cao, Jia
    APPLIED SCIENCES-BASEL, 2023, 13 (02):
  • [2] A Span-based Multi-Modal Attention Network for joint entity-relation extraction
    Wan, Qian
    Wei, Luona
    Zhao, Shan
    Liu, Jie
    KNOWLEDGE-BASED SYSTEMS, 2023, 262
  • [3] Joint multimodal entity-relation extraction based on temporal enhancement and similarity-gated attention
    Wang, Guoxiang
    Liu, Jin
    Xie, Jialong
    Zhu, Zhenwei
    Zhou, Fengyu
    KNOWLEDGE-BASED SYSTEMS, 2024, 304
  • [4] A Two-Phase Paradigm for Joint Entity-Relation Extraction
    Ji, Bin
    Xu, Hao
    Yu, Jie
    Li, Shasha
    Ma, Jun
    Ji, Yuke
    Liu, Huijun
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 74 (01): : 1303 - 1318
  • [5] A multiple head selection joint entity-relation extraction model
    Suo, Jiafeng
    Han, Dongchen
    Zhao, Hui
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 45 (04) : 5647 - 5657
  • [6] Specific Relation Attention-Guided Graph Neural Networks for Joint Entity and Relation Extraction in Chinese EMR
    Pang, Yali
    Qin, Xiaohui
    Zhang, Zhichang
    APPLIED SCIENCES-BASEL, 2022, 12 (17):
  • [7] Joint entity-relation extraction for natural disaster based on table filling
    Cheng, Cheng
    Zeng, Qingtian
    Zhao, Hua
    Wang, Shansong
    JOURNAL OF INFORMATION SCIENCE, 2023,
  • [8] GRAPH CONVOLUTIONAL NETWORKS & ADVERSARIAL TRAINING FOR JOINT EXTRACTION OF ENTITY AND RELATION
    Qu, Xiaolong
    Zhang, Yang
    Tian, Ziwei
    Li, Yuxun
    Li, Dongmei
    Zhang, Xiaoping
    UPB Scientific Bulletin, Series C: Electrical Engineering and Computer Science, 2023, 85 (03): : 213 - 224
  • [9] A Fine-Grained Network for Joint Multimodal Entity-Relation Extraction
    Yuan, Li
    Cai, Yi
    Xu, Jingyu
    Li, Qing
    Wang, Tao
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (01) : 1 - 14
  • [10] GRAPH CONVOLUTIONAL NETWORKS & ADVERSARIAL TRAINING FOR JOINT EXTRACTION OF ENTITY AND RELATION
    Qu, Xiaolong
    Zhang, Yang
    Tian, Ziwei
    LI, Yuxun
    LI, Dongmei
    Zhang, Xiaoping
    UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2023, 85 (03): : 213 - 224