• DocumentCode
    2337586
  • Title

    Sentence compression by structural conversion of parse tree

  • Author

    Egawa, Seiji ; Kato, Yoshihide ; Matsubara, Shigeki

  • Author_Institution
    Grad. Sch. of Inf. Sci., Nagoya Univ., Nagoya
  • fYear
    2008
  • fDate
    13-16 Nov. 2008
  • Firstpage
    544
  • Lastpage
    550
  • Abstract
    Sentence compression is the task of generating a grammatical short sentence from an original sentence, retaining important information. The existing methods of only removing the constituents in the parse tree of an original sentence cannot emulate human compression that changes structures of the parse tree. This paper proposes a method to remove recursive structures, one example of such structural conversions, and generate a grammatical short sentence. In order to remove a recursive structure, our method detects the constituents forming the structure and removes them as a unit. Compression experiments have shown that our method generates more grammatical compressed sentences than the previous method.
  • Keywords
    data compression; grammars; natural language processing; probability; trees (mathematics); grammatical short sentence; parse tree; probability; recursive structure removal; sentence compression; structural conversion; Compression algorithms; Entropy; Humans; Information science; Information technology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Digital Information Management, 2008. ICDIM 2008. Third International Conference on
  • Conference_Location
    London
  • Print_ISBN
    978-1-4244-2916-5
  • Electronic_ISBN
    978-1-4244-2917-2
  • Type

    conf

  • DOI
    10.1109/ICDIM.2008.4746757
  • Filename
    4746757