Improved Statistical Machine Translation Using Monolingual Paraphrases

Abstract

We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems “for free” – by creating it from data that is already available rather than having to create more aligned data. Starting with a syntactic tree, we recursively generate new sentence variants where noun compounds are paraphrased using suitable prepositions, and vice-versa – preposition-containing noun phrases are turned into noun compounds. The evaluation shows an improvement equivalent to 33%–50% of that of doubling the amount of training data.