Follow

Oooh, DeepL has added 13 European languages! Including Danish, Swedish, Hungarian, …

DeepL quality consistently outperforms Google Translate. It's also great because DeepL doesn't use English as common ground between non-English languages. deepl.com/blog/20210316.html

Google Translate can include hilarious errors between non-English languages that clearly show that everything has been translated to English first.

@rixx Wait, is this how Google Translate works?! I never knew!

@rixx Honestly, when AltaVista’s BabelFish was still a thing, I thought it worked better than Google Translate (though Translate obviously improved a lot since).

@Sylvhem @rixx honestly, I could probably count the number of knowledgeable linguists actively working on Google Translate with zero hands

they probably do have direct translation between a few, mostly European languages, but I'd be surprised if that were the case between less common paths like Japanese to Farsi

@rixx The other day, I ran something through Google Translate that translated "Transfeindlichkeit", which I would understand to mean "transphobia", to "transhumanism" 😕

@rixx this isn't by design, but because the majority of Google Translate's training data involves English (because of the Internet).

I think tech-wise, Google Translate and DeepL are fairly similar, but DeepL uses a lot more human-annotated training data.

@russss Yeah, you're right!
I found out that DeepL also fails on corner cases – But, and this is kind of important, it fails by substituting an English term in the A → B translation, whereas Google Translate goes via English into B and loses information. I've seen "to watch" become "a watch" when translating from Hungarian to German (in both languages these words don't share anything).

@russss That's probably just better safeguards and a development team that is more focused on quality, rather than Google-ism, I'd guess.

@rixx So are we reading this wrong, or is every single language they support except for Chinese & Japanese a european one?

@noyovo Do you mean linguistically or geographically?

But yeah, you're right about that otherwise – Google Translate does support more languages at the cost of quality.

@noyovo For what it's worth, it makes a lot of sense to include languages on a family basis as much as you can. I imagine they did Japanese and Chinese for reach, and then focused on family completion in their primary market.

Adding Polish after you have Russian is much easier than adding Finnish. Adding Hungarian while you're adding Finnish is much easier than adding Turkish and so on.

@rixx So they followed the inertia of white supremacy because it's easier, more profitable, or likely both.

@noyovo Yes, I would assume that they optimise for profit.

@rixx but "sziasztok" is directed to many, that is still getting lost, isn't it.

@eneh Define "lost".

Good translations are not precise. Precise translations are not good. "Hi" or the suggested alternative "Hi guys" is a good translation of "Sziasztok". If you want to read up on the topic, "Experiences in translation" by Umberto Eco is a good book to get started. The German translation is, of course, very good (and arguably better than the English one).

@rixx I just got a "Hallo" and well, I am not that fluent in English, wanted to say, that it is not 100%

@eneh Yes, because no translation is ever 100%

@rixx

Deepl is amazing, and my go-to translator for some time.

Super happy to boost this :D

@rixx Oh my goodness! Slovenian is among those 13 languages, too! This is amazing, thank you for sharing!

Sign in to participate in the conversation
chaos.social

chaos.social – a Fediverse instance for & by the Chaos community