Machine Translation




Neutral Machine 

Machine translation (MT) has developed a bad reputation until recently, because using MT-assisted translation memory (TM) was more distracting than helpful. Neural Machine Translation (NMT) is a new technological jump and seems to transform our prejudice with amazing results to a hope for new era. 

 

Using careful controlled authoring, customized MT engines with the most up-to-date glossaries and memories, and human post-editing, MT is now reaching to a stage where it can produce TM quality output faster than TM itself for many types of texts. In general, MT costs will set in between TEP rate and proofreading while productivity get even better when volume is large enough.

Neural Machine translation is a future, as it is fed by rising amount of human-translated bilingual content. Since the first introduction of Trados in 1990s, translation memories have been at work. Now these translation memories represent huge amount of input to Neural Machine Translation. 

 

Postediting

Depending on the projects, NMT may yield favorable results to go for post-editing. Our human post-editors will re-read source and target segments to make sure that the accuracy, consistency, style etc. fit to the purpose.

 

Extra-large content

NMT is able to learn from TMs, which makes it possible to deal with large amount of content by implementing NMT engines and then finalized thought human postediting. 

 

Project management

If machine translation is to be applied to any project, project management, terminology management and quality assurance processes must be carefully taken into consideration.

 

We consider and understand the challenging factors related to machine translation plus post-editing and offer cost-effective solutions.