• DocumentCode
    495249
  • Title

    CRFs-Based Chinese Named Entity Recognition with Improved Tag Set

  • Author

    Guanming, Zeng ; Chuang, Zhang ; Bo, Xiao ; Zhiqing, Lin

  • Author_Institution
    PRIS Lab., Beijing Univ. of Post & Telecommun., Beijing, China
  • Volume
    5
  • fYear
    2009
  • fDate
    March 31 2009-April 2 2009
  • Firstpage
    519
  • Lastpage
    522
  • Abstract
    Chinese named entity recognition is one of the most important tasks in NLP. The paper mainly describes our work on NER tasks. The paper built up a system under the framework of conditional random fields (CRFs) model. With an improved tag set the system gets an F-value of 93.49 using SIGHAN2007 MSRA corpus.
  • Keywords
    natural language processing; probability; CRF-based Chinese named entity recognition; NLP; conditional random field model; improved tag set; natural language processing; Computer science; Costs; Data mining; Graphical models; Hidden Markov models; Markov random fields; Natural languages; Random variables; Text categorization; Text recognition; CRFs; tag set;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Science and Information Engineering, 2009 WRI World Congress on
  • Conference_Location
    Los Angeles, CA
  • Print_ISBN
    978-0-7695-3507-4
  • Type

    conf

  • DOI
    10.1109/CSIE.2009.551
  • Filename
    5170589