Semi-supervised learning for Machine Translation

Statistical machine translation systems are usually trained on large amounts of bilingual text which is used to learn a translation model, and also large amounts of monolingual text in the target language used to train a language model. In this chapter we explore the use of semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. In particular, in this work we use monolingual source language data from the same domain as the test set (without directly using the test set itself) and use semisupervised methods for model adaptation to the test set domain. We propose several algorithms with this aim, and present the strengths and weaknesses of each one. We present detailed experimental evaluations using French–English and Chinese–English data and show that under some settings translation quality can be improved.