Improving translator productivity with MT: a patent translation case study

When evaluating the suitability of MT for post-editing, there are a lot of variables to consider that could have an impact on its overall effectiveness, including: the languages in question, the documents being translated, the translator workflow, and not least the individual translators themselves. Add to that the various ways we can carry out evaluation automatic measures, subjective assessments of fluency and adequacy, etc. and we have got a lot of data on our hands. Despite all of these data points, we are ultimately trying to answer a simple question: is the MT useful and to what extent? In this article, we introduce Iconic Translation Machines and describe a case study on a large-scale post-editing evaluation involving more than 20 translators working on Chinese to English patent translation. We discuss how various evaluations were carried out – from initial MT engine development to translator productivity – and discuss the implications of these findings on the real-world application of MT.