• DocumentCode
    152645
  • Title

    The use of recurrent neural networks language model in Turkish-English machine translation

  • Author

    Yilmaz, Ender ; El-Kahlout, Ilknur Durgar

  • Author_Institution
    BILGEM, TUBITAK, Kocaeli, Turkey
  • fYear
    2014
  • fDate
    23-25 April 2014
  • Firstpage
    1247
  • Lastpage
    1250
  • Abstract
    Turkish with its agglutinative structure needs speacial attention in machine translation research. In this work, a Turkish-English machine translation system is developed for TED1 talks with hierarchical phrase-based machine translation by employing morphological representation for Turkish. Then it is aimed to improve the translation performance by utilizing n-best rescoring with recurrent neural network language model and system combination together.
  • Keywords
    language translation; recurrent neural nets; TED talks; Turkish-English machine translation; agglutinative structure; hierarchical phrase-based machine translation; morphological representation; n-best rescoring; recurrent neural networks language model; translation performance improvement; Computational linguistics; Conferences; Morphology; Pragmatics; Recurrent neural networks; Signal processing; Sun; Recurrent Neural Networks Language Model; Statistical Machine Translation;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Communications Applications Conference (SIU), 2014 22nd
  • Conference_Location
    Trabzon
  • Type

    conf

  • DOI
    10.1109/SIU.2014.6830462
  • Filename
    6830462
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=152645