Structural link prediction model with multi-view text semantic feature extraction

被引:0
|
作者
Chen, Ke [1 ]
Zhang, Tingting [1 ]
Zhao, Yuanxing [2 ]
Qian, Taiyu [3 ]
机构
[1] Nanjing Audit Univ, Sch Comp Sci, Nanjing 211815, Peoples R China
[2] Jinken Coll Technol, Nanjing, Peoples R China
[3] Wuxi Vocat Coll Sci & Technol, Sch Integrated Circuit, Wuxi, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
Multi-view; embedding; semantic; feature extraction; link prediction;
D O I
10.3233/IDT-240022
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The exponential expansion of information has made text feature extraction based on simple semantic information insufficient for the multidimensional recognition of textual data. In this study, we construct a text semantic structure graph based on various perspectives and introduce weight coefficients and node clustering coefficients of co-occurrence granularity to enhance the link prediction model, in order to comprehensively capture the structural information of the text. Firstly, we jointly build the semantic structure graph based on three proposed perspectives (i.e., scene semantics, text weight, and graph structure), and propose a candidate keyword set in conjunction with an information probability retrieval model. Subsequently, we propose weight coefficients of co-occurrence granularity and node clustering coefficients to improve the link prediction model based on the semantic structure graph, enabling a more comprehensive acquisition of textual structural information. Experimental results demonstrate that our research method can reveal potential correlations and obtain more complete semantic structure information, while the WPAA evaluation index validates the effectiveness of our model.
引用
收藏
页码:2421 / 2437
页数:17
相关论文
共 50 条
  • [41] MUNPE:Multi-view uncorrelated neighborhood preserving embedding for unsupervised feature extraction
    Jayashree
    Prakash, T. Shiva
    Venugopal, K. R.
    KNOWLEDGE-BASED SYSTEMS, 2024, 287
  • [42] Automatic multi-view registration of unordered range scans without feature extraction
    Zhu, Jihua
    Zhu, Li
    Li, Zhongyu
    Li, Chen
    Cui, Jingru
    NEUROCOMPUTING, 2016, 171 : 1444 - 1453
  • [43] Subgraph feature extraction based on multi-view dictionary learning for graph classification
    Zheng, Xin
    Liang, Shouzhi
    Liu, Bo
    Xiong, Xiaoming
    Hu, Xianghong
    Liu, Yuan
    KNOWLEDGE-BASED SYSTEMS, 2021, 214
  • [44] Multi-view Sparse Embedding Analysis Based Image Feature Extraction and Classification
    Zhu, Yangping
    Jing, Xiaoyuan
    Wang, Qing
    Wu, Fei
    Feng, Hui
    Wu, Shanshan
    COMPUTER VISION, CCCV 2015, PT II, 2015, 547 : 51 - 60
  • [45] Ensemble multi-view feature set partitioning method for effective multi-view learning
    Singh, Ritika
    Kumar, Vipin
    KNOWLEDGE AND INFORMATION SYSTEMS, 2024, 66 (08) : 4957 - 5001
  • [46] Feature Sampling Based Unsupervised Semantic Clustering for Real Web Multi-View Content
    Gong, Xiaolong
    Huang, Linpeng
    Wang, Fuwei
    THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 102 - 109
  • [47] Hypergraph modeling and hypergraph multi-view attention neural network for link prediction
    Chai, Lang
    Tu, Lilan
    Wang, Xianjia
    Su, Qingqing
    PATTERN RECOGNITION, 2024, 149
  • [48] MV-GCN: Multi-View Graph Convolutional Networks for Link Prediction
    Li, Zhao
    Liu, Zhanlin
    Huang, Jiaming
    Tang, Geyu
    Duan, Yucong
    Zhang, Zhiqiang
    Yang, Yifan
    IEEE ACCESS, 2019, 7 : 176317 - 176328
  • [49] An end-to-end model for multi-view scene text recognition
    Banerjee, Ayan
    Shivakumara, Palaiahnakote
    Bhattacharya, Saumik
    Pal, Umapada
    Liu, Cheng-Lin
    PATTERN RECOGNITION, 2024, 149
  • [50] A Multi-view Approach for Relation Extraction
    Zhou, Junsheng
    Xu, Qian
    Chen, Jiajun
    Qu, Weiguang
    WEB INFORMATION SYSTEMS AND MINING, PROCEEDINGS, 2009, 5854 : 53 - +