On: First AI model that translates 100 languages witho...

[jimmydorry]

This is a pretty huge milestone. However, I really want to see the next generation of MTL. From what I've seen, we're still a long way away from natural sounding translations.

Some pairs are also very bad right now, particularly Korean->English.

[whimsicalism → jimmydorry]

> From what I've seen, we're still a long way away from natural sounding translations.

IMO, this is a dataset problem. I think we're finally seeing the "next generation" of dataset collection in AI so there will be hopefully improvements for pairs with sparser sets.

[jimmydorry → whimsicalism]

Very true. These kinds of problems centre around data set acquisition and validation.

[bloak → jimmydorry]

"Natural-sounding" is much easier to achieve than "correct".

[jimmydorry → bloak]

Is it though? You can construct English sentences that are hard to read, but grammatically correct.

[progfix → jimmydorry]

> we're still a long way away from natural sounding translations.

DeepL makes perfect translations between English and German. Perfect in a sense that it looks like a professional translator translated it. Google, Microsoft, Facebook might be far off, but deepl isn't.

[nestorD → progfix]

Not perfect between English and French but certainly great.

The possibility to insert your corrections in the suggested translation and let the algorithm rewrite the following text make it a huge time saver when one needs to do a translation.

[karmasimida → jimmydorry]

You can try this service (developed by a South Korean company), it is miles better than Google Translate IMO: https://papago.naver.com/

[jimmydorry → karmasimida]

Thanks, i’ll have a look.