Label Incorporated Graph Neural Networks for Text Classification

被引:7
|
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
  • [21] Combining Concept Graph with Improved Neural Networks for Chinese Short Text Classification
    Liao, Jialu
    Sun, Fanke
    Gu, Jinguang
    SEMANTIC TECHNOLOGY, JIST 2019, 2020, 1157 : 205 - 212
  • [22] Self-supervised short text classification with heterogeneous graph neural networks
    Cao, Meng
    Yuan, Jinliang
    Yu, Hualei
    Zhang, Baoming
    Wang, Chongjun
    EXPERT SYSTEMS, 2023, 40 (06)
  • [23] Contrastive knowledge integrated graph neural networks for Chinese medical text classification
    Lan, Ge
    Hu, Mengting
    Li, Ye
    Zhang, Yuzhi
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 122
  • [24] Semisupervised Graph Neural Networks for Graph Classification
    Xie, Yu
    Liang, Yanfeng
    Gong, Maoguo
    Qin, A. K.
    Ong, Yew-Soon
    He, Tiantian
    IEEE TRANSACTIONS ON CYBERNETICS, 2023, 53 (10) : 6222 - 6235
  • [25] Review of Graph Neural Network in Text Classification
    Malekzadeh, Masoud
    Hajibabaee, Parisa
    Heidari, Maryam
    Zad, Samira
    Uzuner, Ozlem
    Jones, James H. Jr Jr
    2021 IEEE 12TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), 2021, : 84 - 91
  • [26] Enhancing Text Classification by Graph Neural Networks With Multi-Granular Topic-Aware Graph
    Gu, Yongchun
    Wang, Yi
    Zhang, Heng-Ru
    Wu, Jiao
    Gu, Xingquan
    IEEE ACCESS, 2023, 11 : 20169 - 20183
  • [27] Connecting the Dots: What Graph-Based Text Representations Work Best for Text Classification using Graph Neural Networks?
    Bugueno, Margarita
    de Melo, Gerard
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EMNLP 2023), 2023, : 8943 - 8960
  • [28] Graph Convolutional Networks for Fast Text Classification
    Cai, Houyv
    Lv, Shaoqing
    Lu, Guangyue
    Li, Tingting
    Proceedings - 2022 4th International Conference on Natural Language Processing, ICNLP 2022, 2022, : 420 - 425
  • [29] Tensor Graph Convolutional Networks for Text Classification
    Liu, Xien
    You, Xinxin
    Zhang, Xiao
    Wu, Ji
    Lv, Ping
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 8409 - 8416
  • [30] JobXMLC: EXtreme Multi-Label Classification of Job Skills with Graph Neural Networks
    Goyal, Nidhi
    Kalra, Jushaan Singh
    Sharma, Charu
    Mutharaju, Raghava
    Sachdeva, Niharika
    Kumaraguru, Ponnurangam
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 2181 - 2191