• DocumentCode
    2084599
  • Title

    Incorporating syntax-based language models in phrase-based SMT models

  • Author

    Chen, Yidong ; Shi, Xiaodong ; Zhou, Changle ; Hong, Qingyang

  • Author_Institution
    Dept. of Cognitive Sci., Xiamen Univ., Xiamen, China
  • Volume
    1
  • fYear
    2008
  • fDate
    17-19 Nov. 2008
  • Firstpage
    808
  • Lastpage
    812
  • Abstract
    In this paper, we proposed a method to incorporate syntax-based language models in phrase-based statistical machine translation (SMT) systems. The language model that we used is based on link grammar, which is a high lexical formalism. In order to apply language models based on link grammar in phrase-based models, we brought out the concept of linked phrases, which is an extension of the concept of traditional phrases in phrase-based models. Experiments were carried out and the results showed that the use of syntax-based language models could improve the performance of the phrase-based models greatly.
  • Keywords
    computational linguistics; language translation; SMT models; high lexical formalism; link grammar; phrase-based models; statistical machine translation; syntax-based language models; Cognitive science; Information retrieval; Information science; Intelligent systems; Knowledge engineering; NIST; Natural languages; Predictive models; Speech recognition; Surface-mount technology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent System and Knowledge Engineering, 2008. ISKE 2008. 3rd International Conference on
  • Conference_Location
    Xiamen
  • Print_ISBN
    978-1-4244-2196-1
  • Electronic_ISBN
    978-1-4244-2197-8
  • Type

    conf

  • DOI
    10.1109/ISKE.2008.4731040
  • Filename
    4731040