UWEE Tech Report Series

Leveraging Multiple Languages to Improve Statistical MT Word Alignments


Karim Filali, Jeff Bilmes

Word alignments, Machine translation, Multilingual processing, Natural Language Processing


This is an extended version of a paper with the same title published in ASRU, 2005. We present a new multilingual statistical MT word alignment model based on a simple extension of the IBM and HMM Models and a two-step alignment procedure. Preliminary results on a small hand-aligned subset of the Europarl corpus show a 7\% relative improvement over a state of the art alignment model.

Download the PDF version

Download the Gzipped Postscript version