Firefox is getting language translation

Re:Firefox is getting language translation by dredmorbius on Tuesday October 22, 2019 @09:39AM (#21323452)

From reports, Google Translate has effectively created its own internal (AI GD ML) metalanguage, which can interpolate between languages it's not been specifically trained on. E.g., with Japanese <-> English and Korean <-> English, Google Translate can manage Japanese <-> Korean, without being specifically trained to do so.

So yes, there's an intermediary language. But it's not English.

https://www.newscientist.com/article/2114748-google-translat...

[ Parent | on HN ]

Re:Firefox is getting language translation by bzbarsky on Tuesday October 22, 2019 @10:00AM (#21323643)

The intermediary language is not English, but due to the way the training set is constructed (pairs of texts in various languages, with the vast majority of pairs having English as one of the languages, is my understanding) it can be very hard to tell apart from English sometimes.

For example, translating "рубанок" ("plane", in the sense of the carpenter's tool) from Russian to Polish used to produce "samolot" ("airplane") in Google translate up until sometime earlier this year, because in the intermediate representation "plane" was ambiguous just like it is in English. It looks like that particular bit is fixed now, which is at least progress! Maybe they've been adding more non-English text pairs...

[ Parent | on HN ]

Re:Firefox is getting language translation by dredmorbius on Tuesday October 22, 2019 @10:36AM (#21324054)

That's almost certainly accurate. The metalanguage / interlingua isn't English, but being based on A <-> English and B <-> English training, is all but certainly influenced by English grammar, words, and idioms, in ways that direct A <->B training would not be.

[ Parent | on HN ]

Re:Firefox is getting language translation by _emacsomancer_ on Tuesday October 22, 2019 @10:00AM (#21323646)

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 the equivalent of 'the sheep came' (भेडा आयो), so somewhere along the line it seemed to be treating the name राम (rām) as equivalent to the English string 'ram' and translating accordingly.

So if the intermediate language isn't English, it certainly has some English-like properties....

[ Parent | on HN ]

Re:Firefox is getting language translation by abhgh on Tuesday October 22, 2019 @02:16PM (#21326924)

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

[ Parent | on HN ]

Re:Firefox is getting language translation by _emacsomancer_ on Tuesday October 22, 2019 @08:37PM (#21329926)

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.

[ Parent | on HN ]

Re:Firefox is getting language translation by TazeTSchnitzel on Tuesday October 22, 2019 @03:09PM (#21327419)

Supposedly, but it behaves suspiciously like English in practice, perhaps because of the input data (lots of texts originally in English then translated to many languages and fed in)

[ Parent | on HN ]