Label Incorporated Graph Neural Networks for Text Classification

被引:6
|
作者
Xin, Yuan [1 ]
Xu, Linli [1 ,3 ]
Guo, Junliang [1 ]
Li, Jiquan [1 ]
Sheng, Xin [1 ]
Zhou, Yuanyuan [2 ]
机构
[1] Univ Sci & Technol China, Sch Comp Sci & Technol, Anhui Prov Key Lab Big Data Anal & Applicat, Hefei, Peoples R China
[2] Univ Sci & Technol China, Informat Sci Ctr, Hefei, Peoples R China
[3] IFLYIEK Co Ltd, Hefei, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
10.1109/ICPR48806.2021.9413086
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Graph Neural Networks (GNNs) have achieved great success on graph-structured data, and their applications on traditional data structures such as natural language processing and semi-supervised text classification have been extensively explored in recent years. While previous works only consider the text information while building the graph, heterogeneous information such as labels is ignored. In this paper, we consider incorporating the label information while building the graph by adding text-label-text paths, through which the supervision information will propagate among the graph more directly. Specifically, we treat labels as nodes in the graph which also contains text and word nodes, and then connect labels with texts belonging to that label. Through graph convolutions, label embeddings are jointly learned with text embeddings in the same latent semantic space. The newly incorporated label nodes will facilitate learning more accurate text embeddings by introducing the label information, and thus benefit the downstream text classification tasks. Extensive results on several benchmark datasets show that the proposed framework outperforms baseline methods by a significant margin.
引用
收藏
页码:8892 / 8898
页数:7
相关论文
共 50 条
  • [1] Recurrent Graph Neural Networks for Text Classification
    Wei, Xinde
    Huang, Hai
    Ma, Longxuan
    Yang, Ze
    Xu, Liutong
    [J]. PROCEEDINGS OF 2020 IEEE 11TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE (ICSESS 2020), 2020, : 91 - 97
  • [2] Graph neural networks for text classification: a survey
    Wang, Kunze
    Ding, Yihao
    Han, Soyeon Caren
    [J]. ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (08)
  • [3] Bipartite Graph Coarsening for Text Classification Using Graph Neural Networks
    dos Santos, Nicolas Roque
    Minatel, Diego
    Baria Valejo, Alan Demetrius
    Lopes, Alneu de A.
    [J]. PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS, COMPUTER VISION, AND APPLICATIONS, CIARP 2023, PT I, 2024, 14469 : 589 - 604
  • [4] BGNN-XML: Bilateral Graph Neural Networks for Extreme Multi-Label Text Classification
    Zong, Daoming
    Sun, Shiliang
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (07) : 6698 - 6709
  • [5] Enhanced Text Classification with Label-Aware Graph Convolutional Networks
    Lin, Ming-Yen
    Liu, Hsuan-Chun
    Hsush, Sue-Chen
    [J]. ELECTRONICS, 2024, 13 (15)
  • [6] Learning neural networks for text classification by exploiting label relations
    Jincheng Xu
    Qingfeng Du
    [J]. Multimedia Tools and Applications, 2020, 79 : 22551 - 22567
  • [7] Multi-label Text Classification with Deep Neural Networks
    Chen, Yun
    Xiao, Bo
    Lin, Zhiqing
    Dai, Cheng
    Li, Zuochao
    Yang, Liping
    [J]. PROCEEDINGS OF 2018 INTERNATIONAL CONFERENCE ON NETWORK INFRASTRUCTURE AND DIGITAL CONTENT (IEEE IC-NIDC), 2018, : 409 - 413
  • [8] Learning neural networks for text classification by exploiting label relations
    Xu, Jincheng
    Du, Qingfeng
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (31-32) : 22551 - 22567
  • [9] Review of Text Classification Methods Based on Graph Neural Networks
    Su, Yilei
    Li, Weijun
    Liu, Xueyang
    Ding, Jianping
    Liu, Shixia
    Li, Haonan
    Li, Guanfeng
    [J]. Computer Engineering and Applications, 2024, 60 (19) : 1 - 17
  • [10] Deep Attention Diffusion Graph Neural Networks for Text Classification
    Liu, Yonghao
    Guan, Renchu
    Giunchiglia, Fausto
    Liang, Yanchun
    Feng, Xiaoyue
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 8142 - 8152