International Workshop on Spoken Language Translation (IWSLT) 2006

Keihanna Science City, Kyoto, Japan
November 27-28, 2006

The University of Washington Machine Translation System for IWSLT 2006

Katrin Kirchhoff (1), Kevin Duh (1), Chris Lim (2)

(1) Department of Electrical Engineering; (2) Department of Computer Science and Engineering
University of Washington, Seattle, USA

This paper describes the University of Washington's submission to the IWSLT 2006 evaluation campaign. We present a multi-pass statistical phrase-based machine translation system for the Italian-English open-data track. The focus of our work was on the use of heterogeneous data sources for training translation and language models, the use of several novel rescoring features in the second pass, and exploiting N-best information for translation in the ASR-output condition. Results show mixed bene&# 2;ts of adding out-of-domain data and using N-best information and demonstrate improvements for some of the novel rescoring features.

Full Paper     Presentation

Bibliographic reference.  Kirchhoff, Katrin / Duh, Kevin / Lim, Chris (2006): "The University of Washington machine translation system for IWSLT 2006", In IWSLT-2006, 145-162.