Phrase-based Machine Translation in a Computer-assisted Translation Environment

We explore the problem of integrating a phrase-based MT system within a computerassisted translation (CAT) environment. We argue that one way of achieving successful integration is to design an MT system that behaves more like the translation memory (TM) component of CAT systems. This implies producing MT output that is consistent with that of a TM when high-similarity material exists in the training data; it also implies providing the MT system with a component that is capable of filtering out machine translations that are less likely to be useful. We propose solutions to both problems, and evaluate their impact on three different data sets. Our results indicate that the proposed approach leads to systems that produce better output than a TM, for a larger portion of the source text.