Total: 1
We present the LIA systems for the machine translation evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2014 for the English-to-Slovene and English-to-Polish translation tasks. The proposed approach takes into account word context; first, it maps sentences into a latent Dirichlet allocation (LDA) topic space, then it chooses from this space words that are thematically and grammatically close to mistranslated words. This original post-processing approach is compared with a factored translation system built with MOSES. While this postprocessing method does not allow us to achieve better results than a state-of-the-art system, this should be an interesting way to explore, for example by adding this topic space information at an early stage in the translation process.