We should previously determine which domains can successfully be processed using MTPE.
Technical domain, user interfaces, medical translations, patent, legal could be more suitable for MT as they consist in usual phrasing and specific terminology that is standardized. Scientific documents with limited vocabulary are also giving great results. By limited, we consider the number of meanings that a word can have. While we are faced with the complexity of the technical/scientific field, we know that the higher the degree of technical complexity is, the more specific the translation of the word must be, and the more likely the machine will choose the right word.
Text that requires a creative approach, marketing, and website contents is not advisable to undergo MT and they need a specific test.
It is quite obvious that the least recommended for machine translation are literary works (novels, poems, etc.) given that they require great interpretative qualities and because the author’s intention is a key element in literature. Therefore, the post-editing job would end up being so large and complicated that we would end up having to re‑translate the whole document.