International Workshop on Spoken Language Translation (IWSLT) 2005

Pittsburgh, PA, USA
October 24-25, 2005

The RWTH Phrase-based Statistical Machine Translation System

Richard Zens, Oliver Bender, Saša Hasan, Shahram Khadivi, Evgeny Matusov, Jia Xu, Yuqi Zhang, Hermann Ney

Human Language Technology and Pattern Recognition, Lehrstuhl für Informatik VI, Computer Science Department, RWTH Aachen University, Aachen, Germany

We give an overview of the RWTH phrase-based statistical machine translation system that was used in the evaluation campaign of the International Workshop on Spoken Language Translation 2005.
   We use a two pass approach. In the first pass, we generate a list of the N best translation candidates. The second pass consists of rescoring and reranking this N-best list. We will give a description of the search algorithm as well as the models that are used in each pass.
   We participated in the supplied data tracks for manual transcriptions for the following translation directions: Arabic-English, Chinese-English, English-Chinese and Japanese-English. For Japanese-English, we also participated in the C-Star track. In addition, we performed translations of automatic speech recognition output for Chinese- English and Japanese-English. For both language pairs, we translated the single-best ASR hypotheses. Additionally, we translated Chinese ASR lattices.

Full Paper    Presentation

Bibliographic reference.  Zens, Richard / Bender, Oliver / Hasan, Saša / Khadivi, Shahram / Matusov, Evgeny / Xu, Jia / Zhang, Yuqi / Ney, Hermann (2005): "The RWTH phrase-based statistical machine translation system", In IWSLT-2005, 145-152.