Live data from Hacker News

Firefox is getting language translation

zdnet.com

111–120 of 129 posts

Re: Firefox is getting language translation

#112

Earlier quoted context omitted.

I am in the translation business, and although we do not use MT so far for the verticals we focus on, perhaps what shocks me most is Deepl Alexa 90-day trend [0]. It is so smooth it seems faked. [0] https://www.alexa.com/siteinfo/deepl.com

Never heard of that website so I give it a try. It says "[t]ranslate from any language", but doesn't seem to support Chinese or Japanese at all. To me, translating other Western languages to English is never a problem. I can use any half-decent online translation services and the result is totally understandable.

"Translate from any language" in the context of deepl.com website means "detect language".

AFAIK, only the devil can translate from any language (not even Google Translate can translate from any language, in spite of attributed evilness to Google).

Re: Firefox is getting language translation

#113
post #108

Earlier quoted context omitted.

> more exotic language pairs I've found that sometimes what Google does for these is translate from Language A > English, and then English > Language B, which leads to bizarre results.

This is pretty standard, even in human (non-automated) translation. One example is technical/service documentation for a heavy machinery company I worked for. The tech writers were based in Germany, but O&M Manuals were required in Japanese for sale in Japan. Those docs were translated using English as a "pivot language". Usually dictated by pricing (fewer German+Japanese translators = much higher cost).

But one advantage of automated translations is that there shouldn't have to be a pivot language.

And in any case, for German->Japanese, going through English probably has a lower cost. But for Hindi->Nepali, you'll lose a lot of information as Hindi and Nepali are closely related and similar not only in terms of correspondences between vocabulary items, but also grammatical structures, which is effectively 'thrown away' if there's an English, or close-enough-to-English-to-effectively-be-English intermediate translation language. (Not to mention the inefficiencies of the equivalent of sending a package from Delhi to Kathmandu via London.....)

Re: Firefox is getting language translation

#114
post #98

Earlier quoted context omitted.

> more exotic language pairs I've found that sometimes what Google does for these is translate from Language A > English, and then English > Language B, which leads to bizarre results.

Since we're complaining about Google Translate, I'd like to mention how ridiculous their "verified translation" system is. It works by throwing automatic translations at people who, in their majority, have never studied English, and expecting them to tell whether it's right or wrong, but what happens is that most just confirm whatever they get as being correct. As a result, at least for Portuguese, many of them, if n…

Well, the more general problem about asking people visiting Google Translate to verify if a translation from A->B is correct is that generally people visiting Google Translate didn't know how to translate A->B or weren't very sure.

How many people on Google Translate actually are able to reasonably verify translations? Relatively few - and those qualified few who might poke at Translate out of curiosity are just as likely not to feel inclined to offer free labour to Google.

> Considering Translate is such an important product, I can't fathom why they just don't hire a single linguist (or just anyone who isn't completely clueless, really) per language to register decent translations, or at least import them from a real dictionary...

Perhaps professional translators rather than linguists. I imagine they have some linguists on the project, but they're likely to be more NLP-type linguists.

The difficulty is that they're interested not just in word-level meaning/translation-accuracy, but also phrase- and clause-level accuracy, and those are really large (i.e. theoretically infinite) spaces.

I've heard that the SpanishEnglish translations aren't too bad.

Re: Firefox is getting language translation

#115
post #102

Earlier quoted context omitted.

It seems to be 'fixed' now, but once I was trying to translate from Hindi to Nepali (which are actually closely-related languages, think Italian and Spanish) with a simple sentence along the lines 'Ram came', where 'Ram' is a common Hindu name (effectively: 'John'), written in Devanagari with a long vowel: राम (rām). And I gave the Hindi input in devanagari (राम आ गया), but still the Nepali translation ended up being…

This is interesting! So its not just about grammatical patterns, but other stuff that might be parsed as named entities.

But it's bizarre that, even if for some reason it doesn't recognise common Indian names, that it just treats 'unknown strings' as English words.

Re: Firefox is getting language translation

#116
post #108

Earlier quoted context omitted.

This is pretty standard, even in human (non-automated) translation. One example is technical/service documentation for a heavy machinery company I worked for. The tech writers were based in Germany, but O&M Manuals were required in Japanese for sale in Japan. Those docs were translated using English as a "pivot language". Usually dictated by pricing (fewer German+Japanese translators = much higher cost).

But one advantage of automated translations is that there shouldn't have to be a pivot language. And in any case, for German->Japanese, going through English probably has a lower cost. But for Hindi->Nepali, you'll lose a lot of information as Hindi and Nepali are closely related and similar not only in terms of correspondences between vocabulary items, but also grammatical structures, which is effectively 'thrown aw…

I think in the case of automated translations it's a function of training data and confidence rather than cost. If you don't have a corpus of translation data for the source/target language combination to draw from, you're essentially forced into a pivot model.

Re: Firefox is getting language translation

#117
post #116

Earlier quoted context omitted.

But one advantage of automated translations is that there shouldn't have to be a pivot language. And in any case, for German->Japanese, going through English probably has a lower cost. But for Hindi->Nepali, you'll lose a lot of information as Hindi and Nepali are closely related and similar not only in terms of correspondences between vocabulary items, but also grammatical structures, which is effectively 'thrown aw…

I think in the case of automated translations it's a function of training data and confidence rather than cost. If you don't have a corpus of translation data for the source/target language combination to draw from, you're essentially forced into a pivot model.

To be frank, the HindiEnglish and NepaliEnglish translation results are pretty poor to start with.

Re: Firefox is getting language translation

#118
post #93
post #63

Earlier quoted context omitted.

Perhaps I'm too jaded, but it comes off to me as copping out of the truly difficult ones!

If you know of a good source for large piles of docs that have been accurately/naturally translated eng/ch/jp, I'm sure deepl would be interested. As another poster pointed out, any deep learning NLP project boils down to quantity+quality of data. I'm assuming adversarial approaches don't work well in this context but I'm not very familiar with nlp research.

Right but that's kind of the essence of machine translation. You won't always have high quality parallel training data for all languages so you have to find a way to thrive with low quality data.

Google has clearly made it their mission to solve that problem, and I'd say they've been rather successful.

Re: Firefox is getting language translation

#119
FWIW, DeepL has restrictions on IP depending on how often you translate things. I've had to connect to various VPNs to continue a conversation without having to login.

It is a good translation tool (and I've used several, Google, Bing) and sure, it's accurate and all but DeepL doesn't compare when it comes to conversational translation or, voice to text etc. If it's simple copy and pasting it does that sufficiently well.

Post reply on HN