[ddmd]

There is a new online translator, http://deepl.com, which relies on deep learning techniques and provides higher (semantic) quality and accuracy of translation. Previously I had quite positive experience with http://translate.yandex.com (but I had to manually compare and combine their results with google translate).

[thomasahle]

> Human: After the defeat, many professors with Pan-Germanistic leanings, who by that time constituted the majority of the faculty, considered it pretty much their duty to protect the institutions of higher learning from “undesirables.” The most likely to be dismissed were young scholars who had not yet earned the right to teach university classes. As for female scholars, well, they had no place in the system at all; nothing was clearer than that.

> Google: After the lost war, many German-National professors, meanwhile the majority in the faculty, saw themselves as their duty to keep the universities from the “odd”; Young scientists were most vulnerable before their habilitation. And scientists did not question anyway; There were few of them.

> DeepL: After the lost war, many German national professors, now the majority of the faculty, regarded it as their duty to protect the universities from the "oddities"; the most defenceless were young scientists from their habilitation. And women scientists were not questioned anyway; there was little agreement on a few things.

I'd say the DeepL translation is slightly better. It still misses most of the points.

[nicois]

I just tried the following, to German, and got the predictable result, which is completely wrong. Until the proper semantic parts of the text are identified, these sorts of mistakes prevent statistical methods from being trustworthy:

Sailing ships in rough seas is asking for trouble

[romseb]

Put a period at the end of the sentence and it changes from

> Segelschiffe in rauer See verlangen Ärger.

to

> Segelschiffe in rauher See sind ein Problem.

[Freak_NL]

The translating software can't distinguish between 'sailing ships' the noun, and 'sailing' (verb) 'ships' (noun) the act. The latter is what is probably intended. It is also missing chances of using idiomatic expressions in the translations.

[claudius]

Well, 'is' is singular so it can’t be the correct verb associated to 'sailing ships' if the latter means multiple sailing ships rather than the activity of sailing ships.

[ddmd]

I like that I can clikc a word in the target box and choose an alternative translation while the system updates the result accordingly. Previously, I had to play with different translation alternatives manually in Google or Yandex translate. I think deepl also learns from such user choices.

[icebraining]

Google Translate lets you do that too..

[akkat]

It used to, but not anymore for long sentences. That is one big reason that I switched.

[raverbashing]

Trying the examples, for the French translation it just doesn't make the last plural mistake, correctly translating "la sienne" (but still missing the subtleties)

The German example is "better" I think, it kinda messes up but in a more predictable way.

"the most defenceless were young scientists from (before) their habilitation"

Also the last phrase is very, very tricky, it actually means "there were only few things people agreed on more" and it was translated as "there was little agreement on a few things."

[heinrichf]

Google definitely switched to deep learning: http://www.nytimes.com/2016/12/14/magazine/the-great-ai-awak... (How Google used artificial intelligence to transform Google Translate)

[1ris]

Result of the example Text from deepl.com:

       At home, they have everything in duplicate. There is her own car and his own car, her own towels and his own towels, her own library and his own library.

It translates it a correctly from French.

[louisswiss]

I use deepl for work (native English speaker with fluent German). The EN-DE translations are brilliant IF you keep sentence construction simple. It also helps to write in a German 'style'.

[taneq]

I think this is what the article would refer to as "writing German using English symbols". You're doing the semantic remapping yourself, such that the system can map from one language directly to the other and end up with a good result.

[tziki]

You think Google doesn't rely on deep learning?