TY - CONF T1 - Using paraphrases for parameter tuning in statistical machine translation T2 - Proceedings of the Second Workshop on Statistical Machine Translation Y1 - 2007 A1 - Madnani,Nitin A1 - Ayan,Necip Fazil A1 - Resnik, Philip A1 - Dorr, Bonnie J AB - Most state-of-the-art statistical machine translation systems use log-linear models, which are defined in terms of hypothesis features and weights for those features. It is standard to tune the feature weights in order to maximize a translation quality metric, using held-out test sentences and their corresponding reference translations. However, obtaining reference translations is expensive. In this paper, we introduce a new full-sentence paraphrase technique, based on English-to-English decoding with an MT system, and we demonstrate that the resulting paraphrases can be used to drastically reduce the number of human reference translations needed for parameter tuning, without a significant decrease in translation quality. JA - Proceedings of the Second Workshop on Statistical Machine Translation T3 - StatMT '07 PB - Association for Computational Linguistics CY - Stroudsburg, PA, USA UR - http://dl.acm.org/citation.cfm?id=1626355.1626371 ER -