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
  • [41] Causal Relation Extraction Based on Graph Attention Networks
    Xu J.
    Zuo W.
    Liang S.
    Wang Y.
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2020, 57 (01): : 159 - 174
  • [42] GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction
    Bian, Junyi
    Huang, Li
    Huang, Xiaodi
    Zhou, Hong
    Zhu, Shanfeng
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 2674 - 2685
  • [43] Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction
    Zhao, Tianyang
    Yan, Zhao
    Cao, Yunbo
    Li, Zhoujun
    PROCEEDINGS OF THE TWENTY-NINTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2020, : 3948 - 3954
  • [44] An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction
    Zaratiana, Urchade
    Tomeh, Nadi
    Holat, Pierre
    Charnois, Thierry
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 17, 2024, : 19477 - 19487
  • [45] Entity-Relation Distribution-Aware Negative Sampling for Knowledge Graph Embedding
    Yao, Naimeng
    Liu, Qing
    Yang, Yi
    Li, Weihua
    Bai, Quan
    SEMANTIC WEB, ISWC 2023, PART I, 2023, 14265 : 234 - 252
  • [46] Entity-Relation Extraction Based on Semantic Operators and Markov Chain Model
    Yang Hong
    Chen Rong
    Liu Ya-qing
    2011 INTERNATIONAL CONFERENCE ON FUTURE COMPUTER SCIENCE AND APPLICATION (FCSA 2011), VOL 4, 2011, : 148 - 151
  • [47] A potential relation trigger method for entity-relation quintuple extraction in text with excessive entities
    Xia, Xiaojun
    Liu, Yujiang
    Fu, Lijun
    COMPUTER SPEECH AND LANGUAGE, 2025, 89
  • [48] Adaptive Graph Convolutional Networks with Attention Mechanism for Relation Extraction
    Li, Zhixin
    Sun, Yaru
    Tang, Suqin
    Zhang, Canlong
    Ma, Huifang
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [49] Dual Attention Guided Graph Convolutional Networks for Relation Extraction
    Li Z.-X.
    Sun Y.-R.
    Tang S.-Q.
    Zhang C.-L.
    Ma H.-F.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2021, 49 (02): : 315 - 323
  • [50] Biomedical cross-sentence relation extraction via multihead attention and graph convolutional networks
    Zhao, Di
    Wang, Jian
    Lin, Hongfei
    Wang, Xin
    Yang, Zhihao
    Zhang, Yijia
    APPLIED SOFT COMPUTING, 2021, 104