• DocumentCode
    3102004
  • Title

    The Automatic Analysis of Chunk-Extension Sentences

  • Author

    Wei, Xiangfeng ; Zhang, Quan

  • Author_Institution
    Inst. of Acoust., Chinese Acad. of Sci., Beijing, China
  • fYear
    2009
  • fDate
    7-9 Dec. 2009
  • Firstpage
    177
  • Lastpage
    181
  • Abstract
    The chunk-extension sentence is a kind of sentence, which is defined with specific conceptual knowledge in the theory of hierarchical network of concepts. This paper introduces some semantic categories of chunk-extension sentences and related typical verbs. By these typical verbs, the eigen semantic chunk and semantic category of a chunk-extension sentence can be activated. The semantic structure of a sentence can be revealed after testing with the transcendent conceptual knowledge of chunk-extension semantic categories. An experiment was done for automatically analyzing chunk-extension sentences based on a system of analyzing the semantic categories of sentences. The precision of the experiment is 71.29%. The errors are mainly caused when recognizing the head verb and selecting the right semantic category from the multi-semantic-category of a verb. The well analyzing result of chunk-extension sentences will be helpful to tackle the multi-verb puzzle in processing Chinese sentences.
  • Keywords
    eigenvalues and eigenfunctions; natural language processing; Chinese sentence processing; chunk-extension semantic categories; chunk-extension sentence automatic analysis; eigen semantic chunk; hierarchical network of concept theory; multisemantic category; multiverb puzzle; semantic structure; transcendent conceptual knowledge; Acoustics; Degradation; Humans; Joining processes; Natural languages; Skeleton; Testing; chunk-extension; semantic chunk; sentence category (SC); the theory of HNC;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Asian Language Processing, 2009. IALP '09. International Conference on
  • Conference_Location
    Singapore
  • Print_ISBN
    978-0-7695-3904-1
  • Type

    conf

  • DOI
    10.1109/IALP.2009.45
  • Filename
    5380761