This paper describes ATR’s hybrid approach to spoken language translation and it’s application to the IWSLT 2005 translation task. Multiple corpus-based translation engines are used to translate the same input, whereby the best translation among the element MT outputs is selected according to statistical models. The evaluation results of the Japanese-to-English and Chinese-to-English translation tasks for different training data conditions showed the potential of the proposed hybrid approach and revealed new directions in how to improve the current system performance. 1.

This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system. 1.

Project funded by the European Community under the Sixth Framework Programme for Research and Technological Development. Project ref no. IST-034291

This paper reports the latest performance of components and features of a project named Corpus- Centered Computation (cS), which targets a trans- lation technology suitable for spoken language translation. C s places corpora at the center of the technology. Translation knowledge is extracted from corpora by both EBMT and SMT methods, translation quality is gauged by re)brring to corpora, the best translation among multiple-engine outputs is selected based on corpora and the corpora themselves are paraphrased or filtered by automated processes.

In one form or another language translation is a necessary part of cross-lingual information retrieval systems. Often times this is accomplished using machine translation systems. However, machine translation systems offer low quality for their high costs. This paper proposes a machine translation method that is low cost while improving translation quality. This is done by utilizing multiple web based translation services to negate the high cost of translation. A best translation is chosen from the candidates using either consensus translation selection or statistical analysis. Which to use is determined by a heuristic rule that takes into account that most web based translation services are of similar quality and that machine translation still produces relatively poor results. By choosing the best translation the method is able to increase translation quality over the base systems, which is verified by the experimentation.