%0 Conference Paper %B Proceedings of the Second Workshop on Statistical Machine Translation %D 2007 %T Using paraphrases for parameter tuning in statistical machine translation %A Madnani,Nitin %A Ayan,Necip Fazil %A Resnik, Philip %A Dorr, Bonnie J %X 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. %B Proceedings of the Second Workshop on Statistical Machine Translation %S StatMT '07 %I Association for Computational Linguistics %C Stroudsburg, PA, USA %P 120 - 127 %8 2007/// %G eng %U http://dl.acm.org/citation.cfm?id=1626355.1626371