DeepL develops artificial intelligence for understanding and translating texts. She will support you from today.
Some time ago I discovered DeepL.com and used it to translate my stuff since then.
I used Google Translator a lot before because it was fast, had an app for android and considered suggestions from users for corrections.
DeepL has an impressive amount of computing capacity in the background which makes it so fast.
As a german I got curious how the german project will evolve.
The company
There was a company called Linguee GmbH from Cologne, Germany. Shortly before the launch of DeepL, they changed their name to DeepL GmbH and published the translation platform on the 28th of August 2017.
The technology
DeepL is using supercomputers based in Iceland with more than 5.1 petaFLOPS! The database was trained to the database of Linguee pre-launch.
It uses Convolutional Neural Networks behind the scenes.
Personal opinion
- Fast
- Translation while typing
- Same performance on mobile devices!
- Best translations so far (detection of context, meanings)
- Language detection works like a charm! Load website, type right away, copy result, close - done!
I want to draw attention to DeepL translation service because my collegues and I are using it a lot now and are thrilled with it!
Maybe it comes in handy for some of you, too.
Leave your thoughts on it in the comments.
Top comments (2)
I agree wholeheartedly with you, Robin. I have tested DeepL on a difficult philosophical article and on the text of a children’s book. (E->F in both cases). I find DeepL absolutely tremendous. It doesn’t think, of course, but that’s not really the point. Its output is way superior to Google’s or Bing’s and even to the translation of the published children’s book.
I am a professional translator (retired from the UN after a little over a quarter-century in the salt mines :).
Wow that is nice, Roger. This supports my decision to keep on using it. I agree completely with you that the results are way better than Google's and Bing's results.
Thank you for your feedback :)