SyMGiza++: Symmetrized Word Alignment Models for Statistical Machine Translation

  title={SyMGiza++: Symmetrized Word Alignment Models for Statistical Machine Translation},
  author={Marcin Junczys-Dowmunt and Arkadiusz Szal},
SyMGiza++ — a tool that computes symmetric word alignment models with the capability to take advantage of multi-processor systems — is presented. A series of fairly simple modifications to the original IBM/Giza++ word alignment models allows to update the symmetrized models between chosen iterations of the original training algorithms. We achieve a relative alignment quality improvement of more than 17% compared to Giza++ and MGiza++ on the standard Canadian Hansards task, while maintaining the… CONTINUE READING
Highly Cited
This paper has 21 citations. REVIEW CITATIONS


Publications citing this paper.

Similar Papers

Loading similar papers…