News for hackers. Stuff that matters.
Re:Natural language isn’t just English [pdf] by simias on Wednesday December 25, 2019 @07:16AM (#21878203)
I can definitely attest for the English bias of Google translate, even if you're translating between pairs of languages that don't include English. In particular, as you point out, it's often confused by English homonyms (even if they're not homonyms in either the source or target language).

For instance attempting to translate Portuguese "o báculo" (the staff, the object) into French gives you "le personnel" (the staff, people working together). It's a completely wrong translation that, I'm guessing, is caused by the algorithm not managing to differentiate these two different meanings because they're homonyms in English: https://translate.google.com/#view=home&op=translate&sl=pt&t...

An other thing Google translate is terrible at is handling the various level of addressing. Many languages have the notion of polite vs informal "you" (you/thou) which have mostly disappeared from modern English. Google very often translates a formal/polite form of address into an informal one, or vice versa: https://translate.google.com/#view=home&op=translate&sl=fr&t...

Here the polite French "how are you" is translated with the informal "ты" in Russian instead of "вы". Interestingly if I then translate in the other way around it correctly uses the "tu" form in French: https://translate.google.com/#view=home&op=translate&sl=ru&t...

Re:Natural language isn’t just English [pdf] by Veedrac on Wednesday December 25, 2019 @11:00AM (#21878988)
This is simply because Google Translate relies on language-language models trained on language-language pairs. Where training data is not available in quantity, the quality of translations is sufficiently low that going through English is preferred.

This is something that has been solved recently[1] by training ‘massively multilingual’ models. However, such models come with fairly stark compute costs, especially given the number of users Google Translate has, so it will take a while for these advances to roll out. Which ultimately points out how silly this article is: NLP is all the same in relevant matters, and (to first approximation) what works for English works for everything else too, as long as you can get enough training data.

[1] https://ai.googleblog.com/2019/10/exploring-massively-multil...

Re:Natural language isn’t just English [pdf] by TazeTSchnitzel on Wednesday December 25, 2019 @11:16AM (#21879065)
> what works for English works for everything else too

…if they're similar to English. Which isn't good enough, there are many important languages that are quite different from English.

Re:Natural language isn’t just English [pdf] by Veedrac on Wednesday December 25, 2019 @11:23AM (#21879114)
They're all similar to English. Languages have their syntactic ambiguities in different places, but they're all fundamentally similar. In every case the hard part is in understanding the semantics expressed, and the characters used to express it are a side-issue.
Re:Natural language isn’t just English [pdf] by _emacsomancer_ on Wednesday December 25, 2019 @11:52AM (#21879251)
They're similar at the atomic level, so to speak, but not very similar at the levels relevant for translation.

The characters used to express languages are certainly a side-issue, but I don't understand why you would bring that into a discussion of syntactic structure.

For compositional semantics, understanding the syntactic structures involved is crucial. Otherwise you end up with gibberish (i.e. what I find so often with Google Translate).

Re:Natural language isn’t just English [pdf] by Veedrac on Wednesday December 25, 2019 @12:08PM (#21879344)
My claim isn't that it's easy to solve NLP; of course a resource-constrained system like Google Translate that inderects many language pairs through English is going to have glaring issues.

My claim is that the challenges generalize between languages. If you can handle English, you can handle any other language, and while the easy parts might at least look different at the surface, the hard parts are all the same.

Re:Natural language isn’t just English [pdf] by TazeTSchnitzel on Wednesday December 25, 2019 @11:27AM (#21879132)
This is assuming the problems are similar between languages. But are they? An NLP system tested only on English might be useless on CJK languages, because they do not use spaces, so the system cannot rely on the almost-free segmentation you get from English. Another example is that if you try a heavily-inflected language, you suddenly have vastly more forms of the same word than in English, and your system needs to be robust to that in a way that's unnecessary for English.
Re:Natural language isn’t just English [pdf] by Veedrac on Wednesday December 25, 2019 @11:40AM (#21879193)
An NLP model that can't even (implicitly) segment CJK languages is laughable. It's like saying ‘sure, Magnus Carlsen is really good at chess, but in draughts you can take multiple moves in a row.’ If you can handle the ambiguities in natural casual English, you can handle a little inflection.
Re:Natural language isn’t just English [pdf] by TazeTSchnitzel on Wednesday December 25, 2019 @11:30AM (#21879150)
Translating via English consistently creates nonsense even in similar languages (English and Swedish!). Though Google Translate can't even get English right, it thinks “cheque” (the monetary instrument) can be translated to the Swedish verb corresponding “check” (to look at) :D