Fluency enhancement of machine translation

The quality of machine translation can often be poor due to it appearing incoherent and lacking in fluency. These problems consist of word ordering, awkward use of words and grammar, and translating text too literally. However we should not consider translations such as these failures until we have done our best to enhance the quality of the translations, or in other words, the fluency. In the same way various techniques can be applied to touch up a photograph, various techniques can also be applied to touch up a translation. This paper outlines fluency enhancement techniques that improve the quality of machine translation to a higher degree. Furthermore it explores the concept that, if multiple translations are generated from the same source text, then with the addition of fluency enhancement, the quality of these translations are quite competitive. Therefore the top few are quite worthy candidates for a final translation. Lastly, massive corpora prepared by Google and Kaleido K Translation are used to power the fluency enhancement techniques and the translation direction of Korean to English will be used to provide examples and explanations.