International Workshop on Spoken Language Translation (IWSLT) 2006

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

The UKA/CMU Statistical Machine Translation System for IWSLT 2006

Matthias Eck (1), Ian Lane (2), Nguyen Bach (2), Sanjika Hewavitharana (2), Muntsin Kolss (1), Bing Zhao (2), Almut Silja Hildebrand (1), Stephan Vogel (2), Alex Waibel (1,2)

InterACT Research Laboratories:
(1) University of Karlsruhe, Karlsruhe, Germany; (2) Carnegie Mellon University, Pittsburgh, USA

This paper describes the UKA/CMU statistical machine translation system used in the IWSLT 2006 evaluation campaign. The system is based on phrase-to-phrase translations extracted from a bilingual corpus. We compare two different phrase alignment techniques both based on word alignment probabilities. The system was used for all language pairs and data conditions in the evaluation campaign translating both the ASR output (as 1best) and the correct recognition results.

Full Paper     Presentation

Bibliographic reference.  Eck, Matthias / Lane, Ian / Bach, Nguyen / Hewavitharana, Sanjika / Kolss, Muntsin / Zhao, Bing / Hildebrand, Almut Silja / Vogel, Stephan / Waibel, Alex (2006): "The UKA/CMU statistical machine translation system for IWSLT 2006", In IWSLT-2006, 130-137.