We present a discriminative learning method to improve the consistency of translations in phrase-based Statistical Machine Translation (SMT) systems. Our method is inspired by Translation Memory (TM) systems which are widely used by human translators in industrial settings. We constrain the translation of an input sentence using the most similar ‘translation example ’ retrieved from the TM. Differently from previous research which used simple fuzzy match thresholds, these constraints are imposed using discriminative learning to optimise the translation performance. We observe that using this method can benefit the SMT system by not only producing consistent translations, but also improved translation outputs. We report a 0.9 point improvement in terms of BLEU score on English–Chinese technical documents. 1

An enormous potential exists for solving certain classes of computational problems through rich collaboration among crowds of humans supported by computers. Solutions to these problems used to involve human professionals who are expensive to hire or difficult to find. Despite significant advances, fully automatic systems still have much room for improvement. Recent research has involved recruiting large crowds of skilled humans (“crowdsourcing”), but crowdsourcing solutions are still restricted by the availability of those skilled human participants. With translation, for example, professional translators incur high cost and are not always available; machine translation systems have been greatly improved recently, but still can only provide passable translation, and for only limited language pairs at that; crowdsourced translation is limited by the availability of bilingual humans. This dissertation describes crowdsourced monolingual translation, where monolingual translation is translation performed by monolingual people. Crowdsourced monolingual translation is a collaborative form of translation performed by two crowds of people