• DocumentCode
    3545996
  • Title

    Chinese-English Chunk Alignment Based on Anchor Chunk

  • Author

    Sikuan, Wang ; Yanquan, Zhou

  • Author_Institution
    Sch. of Comput. Sci., Beijing Univ. of Posts & Telecommun., Beijing, China
  • fYear
    2009
  • fDate
    21-22 Nov. 2009
  • Firstpage
    398
  • Lastpage
    401
  • Abstract
    A new statistical method called "bilingual chunking" for structure alignment is proposed. Different with the existing approaches which align hierarchical structures like sub-trees, our method conducts alignment on chunks. The alignment is finished through a simultaneous bilingual chunking algorithm. Using the constrains of chunk correspondence between source language (SL) and target language (TL), our algorithm can dramatically reduce search space, support time synchronous DP algorithm, and lead to highly consistent chunking. Furthermore, by unifying the POS tagging and chunking in the search process, our algorithm alleviates effectively the influence of POS tagging deficiency to the chunking result.
  • Keywords
    dynamic programming; natural language processing; statistical analysis; Chinese-English chunk alignment; POS tagging; anchor chunk; dynamic programming; simultaneous bilingual chunking algorithm; source language; statistical method; target language; time synchronous DP algorithm; Application software; Computer science; Entropy; Information technology; Intelligent structures; Machine learning; Machine learning algorithms; Natural languages; Statistical analysis; Tagging; Phrase alignment; dynamic programming; machine learning; maximum entropy;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Information Technology Application Workshops, 2009. IITAW '09. Third International Symposium on
  • Conference_Location
    Nanchang
  • Print_ISBN
    978-1-4244-6420-3
  • Electronic_ISBN
    978-1-4244-6421-0
  • Type

    conf

  • DOI
    10.1109/IITAW.2009.124
  • Filename
    5419598