Generation of Word Graphs in Statistical Machine Translation

Nicola Ueffing,F. Och,H. Ney

Published 2002 in Conference on Empirical Methods in Natural Language Processing

ABSTRACT

Statistical machine translation systems usually compute the single sentence that has the highest probability according to the models that are trained on data. We describe a method for constructing a word graph to represent alternative hypotheses in an efficient way. The advantage is that these hypotheses can be rescored using a refined language or translation model. Results are presented on the German-English Verbmobil corpus.

PUBLICATION RECORD

  • Publication year

    2002

  • Venue

    Conference on Empirical Methods in Natural Language Processing

  • Publication date

    2002-07-06

  • Fields of study

    Linguistics, Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

CITED BY

Showing 1-100 of 138 citing papers · Page 1 of 2