• DocumentCode
    2021167
  • Title

    Segmental HMM-based Part-of-speech tagger

  • Author

    Bokaei, Mohammad Hadi ; Sameti, Hossein ; Bahrani, Mohammad ; BabaAli, Bagher

  • Author_Institution
    Speech Process. Lab., Sharif Univ. of Technol., Tehran, Iran
  • fYear
    2010
  • fDate
    23-25 Nov. 2010
  • Firstpage
    52
  • Lastpage
    56
  • Abstract
    This paper presents a solution in order to solve the problem of using HMM-based POS tagger in some languages where a word can be comprised of several tokens. Viterbi algorithm is modified in order to support segment of words within a model state. In the other word, the proposed system has a built-in tokenizer where indicates words boundaries as well as its corresponding tag sequence.
  • Keywords
    Viterbi decoding; hidden Markov models; speech coding; Viterbi algorithm; built-in tokenizer; hidden Markov models; languages; part-of-speech tagger; segmental HMM; tag sequence; word segment; Accuracy; Hidden Markov models; Speech; Speech processing; Syntactics; Tagging; Viterbi algorithm;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Audio Language and Image Processing (ICALIP), 2010 International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-5856-1
  • Type

    conf

  • DOI
    10.1109/ICALIP.2010.5685018
  • Filename
    5685018