Language Modeling for Verbatim Translation Task

In this paper we present the first results towards finding the better TC-STAR 2006 verbatim transcription system configuration by means of improving the quality of language model performance. There is a present lack of research devoted to special techniques of verbatim translation, therefore we have made an attempt to improve translation accuracy by combining the Final Text Edition (FTE) system with supplementary verbatim corpus. Our work was focused on finding the best combination of the baseline (FTE) and verbatim language models for Spanish-English and English-Spanish language pairs. In order to improve the overall system performance standard n-gram based statistical machine translation (SMT) system was supplemented with a log linear combination of some additional feature functions and linguistically motivated word reordering technique. In the final part of the study we report the results of the baseline system translation accuracy in comparison with the FTE-verbatim interpolated language model systems for various proportions of the language models linear combination.