Computing consensus translation from multiple machine translation systems using enhanced hypotheses alignment

  • Matusov E
  • Ueffing N
  • Ney H
  • 19


    Mendeley users who have this article in their library.
  • 54


    Citations of this article.


the outputs of multiple machine trans- lation (MT) systems. The outputs are combined and a possibly new transla- tion hypothesis can be generated. Similarly to the well-established ROVER approach of (Fiscus, 1997) for combining speech recognition hypotheses, the con- sensus translation is computed by voting on a confusion network. To create the con- fusion network, we produce pairwiseword alignments of the original machine trans- lation hypotheses with an enhanced sta- tistical alignment algorithm that explicitly models word reordering. The context of a whole document of translations rather than a single sentence is taken into account to produce the alignment. The proposed alignment and voting ap- proach was evaluated on several machine translation tasks, including a large vocab- ulary task. The method was also tested in the framework of multi-source and speech translation. On all tasks and conditions, we achieved significant improvements in translation quality, increasing e. g. the BLEU score by as much as 15% relative

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

  • PUI: 372250696
  • SCOPUS: 2-s2.0-79960276653
  • SGR: 79960276653
  • ISBN: 1932432590


  • Evgeny Matusov

  • Nicola Ueffing

  • Hermann Ney

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free