Miroslav Pošta’s English abstract
Have you ever wondered what it would be like if you had a little Google Translate in your computer that would learn from your translations and could be used to translate even those confidential texts that cannot leave your machine? With Slate™ Desktop, this is possible.
First, you have to feed your translation memories into the programme and let it process the data, ideally overnight. What you get is a customized translation engine which mimics your choices. It is hard to say how much data the programme needs – it depends on the language combination you work in and the type of the text you need to translate – but from users’ experience, engines built with memories of 80 thousand and more segments tend to produce good results. (The original article illustrates the quality of output by comparing results from two engines, one built with 214k segments, the other with 10.5k segments.) Anyway, this doesn’t mean that only size matters. Users of Slate Desktop report that subject-specific translation memories with 100,000 segments often work better than translation memories with a million of segments.
In my test translation suggests (a link to the complete file will be provided in the article), many of the words don’t need any editing at all, while some only require editing of word endings. Even if you use just 25% or 15% of the output, it can save you a lot of time. It would be wrong to take a black-and-white approach, which is so common in mainstream media covering machine translation. We shouldn’t expect the machine to produce either perfect or totally useless translation – instead, we should ask: Are the suggestions we get from the MT system useful? Do they save time? Do they improve the overall quality of human translation? Everyone should try for themselves.
Myself, I’m going to use Slate Desktop for some types of translation. (And I’ve learned an important lesson: translation memories are a valuable asset which deserves good management. Therefore, I’m going to take better care of my TMs.) What I also like about Slate Desktop is that it empowers the translator: it allows ordinary professionals to use technologies that otherwise tend to be accessible only to the big players. Now it’s up to translators to decide if they’ll ride the tidal wave of modern technology or let it sweep them away.