Edinburgh System Description for the 2006 TC-STAR Spoken Language Translation Evaluation

In this paper we describe the Edinburgh University statisti cal machine translation system, as used for the TC-STAR 2006 evaluation campaign. We participated in the primary Final Text Edition track for the Spanish to English and English to Spanish translation tasks, using only the provided datasets for training our translati on and language models. We obtained the highest WNM/Recall score in both language pairs and had competitive results for all other evaluation metrics.