• DocumentCode
    2544582
  • Title

    Textual chunk retrieval and packing in pattern

  • Author

    Jin, Bo ; Shi, Yan-Jun ; Teng, Hong-Fei

  • Author_Institution
    Sch. of Innovation Exp., Dalian Univ. of Technol., Dalian, China
  • fYear
    2010
  • fDate
    16-18 April 2010
  • Firstpage
    301
  • Lastpage
    305
  • Abstract
    Pattern technology of writing is widely used in machine writing systems. In pattern technology, there are two core issues about chunk as writing material in the pattern. One is chunk retrieval, the other is chunk packing. In this study, we focus on the problem of chunk retrieval and packing with given style, topic and content of practical writing. We proposed the concept of chunk, and discussed the method of chunk retrieval in context. Then we studied the approach of chunk packing. Differ from general packing problem, chunk packing is affected by several special factors: stylistic features, writing model, literal semantic and etc. These require the intelligence of human. Thus our chunk packing approach is based on man-machine cooperation genetic algorithm. The man-machine cooperation approach can realize the integration of the human and the machine to finish the writing process.
  • Keywords
    genetic algorithms; natural language processing; pattern recognition; text analysis; chunk packing; machine writing systems; man-machine cooperation genetic algorithm; textual chunk retrieval; writing pattern technology; Artificial intelligence; Content based retrieval; Genetic algorithms; Humans; Internet; Libraries; Man machine systems; Natural languages; Technological innovation; Writing; chunk; packing; pattern technique; retrieval;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Management and Engineering (ICIME), 2010 The 2nd IEEE International Conference on
  • Conference_Location
    Chengdu
  • Print_ISBN
    978-1-4244-5263-7
  • Electronic_ISBN
    978-1-4244-5265-1
  • Type

    conf

  • DOI
    10.1109/ICIME.2010.5477651
  • Filename
    5477651