English-to-Czech factored machine translation

  • Authors:
  • Ondřej Bojar

  • Affiliations:
  • Institute of Formal and Applied Linguistics, ÚFAL MFF UK, Praha, Czech Republic

  • Venue:
  • StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes experiments with English-to-Czech phrase-based machine translation. Additional annotation of input and output tokens (multiple factors) is used to explicitly model morphology. We vary the translation scenario (the setup of multiple factors) and the amount of information in the morphological tags. Experimental results demonstrate significant improvement of translation quality in terms of BLEU.