A Topic-based Document Retrieval System Architecture

被引:0
|
作者
Jia, Xiping [1 ]
机构
[1] Guangdong Polytech Normal Univ, Sch Comp Sci, Guangzhou, Guangdong, Peoples R China
关键词
information retrieval; machine learning; topic; document retrieval;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A Topic-based Document Retrieval System Architecture (TDRSA) is proposed in this paper to weaken the discount of document retrieval precision caused by synonymy and polysemy. The TDRSA includes three tiers: Retrieval application, Retrieval algorithm and Data. Analysis shows that TDRSA has the following characteristics: (1) emphasizing the document semantic learning; (2) low dimension in document representation; (3) weakening the discount of document retrieval precision caused by synonymy and polysemy in theory.
引用
收藏
页码:80 / 83
页数:4
相关论文
共 11 条
  • [1] [Anonymous], ACL 94
  • [2] Baeza-Yates R.A., 1999, Modern Information Retrieval
  • [3] Becker J., 2003, Proceedings of the 6th International Conference on Business Information Systems, P7
  • [4] Latent Dirichlet allocation
    Blei, DM
    Ng, AY
    Jordan, MI
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) : 993 - 1022
  • [5] Hofmann T, 1999, UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, PROCEEDINGS, P289
  • [6] A topic-based document correlation model
    Jia, Xi-Ping
    Peng, Hong
    Zheng, Qj-Lun
    Jiang, Zhuo-Lin
    Li, Zhao
    [J]. PROCEEDINGS OF 2008 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2008, : 2487 - 2491
  • [7] Jia Xi-ping, 2008, Journal of South China University of Technology, V36, P37
  • [8] Probabilistic document correlation model
    Jia, Xiping
    Peng, Hong
    [J]. CIS WORKSHOPS 2007: INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY WORKSHOPS, 2007, : 433 - 436
  • [9] LOVASZ L, 1986, MATCHING THEORY, P1
  • [10] Papadimitriou C. H., 1998, Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems. PODS 1998, P159, DOI 10.1145/275487.275505