International Workshop on Spoken Language Translation (IWSLT) 2007
This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2007 evaluation campaign. We participated in three of the four language pair translation tasks (CE, JE, and IE). We used a phrase-based SMT system using log-linear feature models for all tracks. This year we decoded from the ASR n-best lists in the JE track and found a gain in performance. We also applied some new techniques to facilitate the use of out-of-domain external resources by model combination and also by utilizing a huge corpus of n-grams provided by Google Inc.. Using these resources gave mixed results that depended on the technique also the language pair however, in some cases we achieved consistently positive results. The results from model-interpolation in particular were very promising.
Full Paper Presentation
Bibliographic reference. Finch, Andrew / Denoual, Etienne / Okuma, Hideo / Paul, Michael / Yamamoto, Hirofumi / Yasuda, Keiji / Zhang, Ruiqiang / Sumita, Eiichiro (2007): "The NICT/ATR speech translation system for IWSLT 2007", In IWSLT-2007, 103-110.