An Effective Knowledgeable Label-Aware Approach for Sentential Relation Extraction

被引:0
|
作者
Nie, Binling [1 ]
Shao, Yiming [1 ]
机构
[1] Hangzhou Dianzi Technol Univ, Digital Media Sch, Hangzhou 310000, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 21期
关键词
sentential relation extraction; knowledge graph; label-aware;
D O I
10.3390/app132111929
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In recent years, sentential relation extraction has made remarkable progress with text and knowledge graphs (KGs). However, existing architectures ignore the valuable information contained in relationship labels, which KGs provide and can complement the model with additional signals and prior knowledge. To address this limitation, we propose a neural architecture that leverages knowledgeable labels to enhance sentential relation extraction. We name our proposed method knowledge label-aware sensitive relation extraction (KLA-SRE). To achieve this, we combine pre-trained static knowledge graph embeddings with learned semantic embeddings from other tokens to efficiently represent relation labels. By combining static pre-trained graph embeddings with learned word embeddings, we mitigate the inconsistency between predicted relations and given entities. Experimental results on various relation extraction benchmarks in different fields show that knowledge labels improve the F1 score by 1.6% and 1.1% on average over the baseline on standard- and minority-shot benchmarks, respectively.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] Enhanced Text Classification with Label-Aware Graph Convolutional Networks
    Lin, Ming-Yen
    Liu, Hsuan-Chun
    Hsush, Sue-Chen
    ELECTRONICS, 2024, 13 (15)
  • [22] Label-Aware Global Consistency for Multi-Label Learning with Single Positive Labels
    Xie, Ming-Kun
    Xiao, Jia-Hao
    Huang, Sheng-Jun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [23] Label-Aware Chinese Event Detection with Heterogeneous Graph Attention Network
    Cui, Shi-Yao
    Yu, Bo-Wen
    Cong, Xin
    Liu, Ting-Wen
    Tan, Qing-Feng
    Shi, Jin-Qiao
    JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2024, 39 (01) : 227 - 242
  • [24] Zero-shot Label-Aware Event Trigger and Argument Classification
    Zhang, Hongming
    Wang, Haoyu
    Roth, Dan
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 1331 - 1340
  • [25] Label-Aware Hyperbolic Embeddings for Fine-grained Emotion Classification
    Chen, Chih-Yao
    Hung, Tun-Min
    Hsu, Yi-Li
    Ku, Lun-Wei
    PROCEEDINGS OF THE 61ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023): LONG PAPERS, VOL 1, 2023, : 10947 - 10958
  • [26] Text multi-label learning method based on label-aware attention and semantic dependency
    Liu, Baisong
    Liu, Xiaoling
    Ren, Hao
    Qian, Jiangbo
    Wang, YangYang
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (05) : 7219 - 7237
  • [27] Trigger is Non-central: Jointly event extraction via label-aware representations with multi-task learning
    Lv, Jianwei
    Zhang, Zequn
    Jin, Li
    Li, Shuchao
    Li, Xiaoyu
    Xu, Guangluan
    Sun, Xian
    Knowledge-Based Systems, 2022, 252
  • [28] Text multi-label learning method based on label-aware attention and semantic dependency
    Baisong Liu
    Xiaoling Liu
    Hao Ren
    Jiangbo Qian
    YangYang Wang
    Multimedia Tools and Applications, 2022, 81 : 7219 - 7237
  • [29] Enhancing semi-supervised learning through label-aware base kernels
    Wang, Qiaojun
    Zhang, Kai
    Chen, Zhengzhang
    Wang, Dequan
    Jiang, Guofei
    Marsic, Ivan
    NEUROCOMPUTING, 2016, 171 : 1335 - 1343
  • [30] Label-Aware Neural Tangent Kernel: Toward Better Generalization and Local Elasticity
    Chen, Shuxiao
    He, Hangfeng
    Su, Weijie J.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33