It’s particularly obvious if you translate between languages with vastly different grammar, e.g. Korean -> English, since Korean doesn’t require a subject per sentence but English does – so Google Translate then sometimes just inserts random subjects from its training data into the translated text. ChatGPT, by understanding more of the context before each sentence in a long text, seems to do this less.
For stuff like French -> English or German -> English where there is “no missing info” per sentence to create grammatically correct sentences, so that it doesn’t need to rely on context to translate correctly, Google Translate is great.
When accuracy is absolutely critical, don’t depend on machine translation alone, and especially don’t depend on a single machine translation without cross checking it. As it is, I have anecdotally only had good experiences when comparing GPT-4o’s translation quality to Google Translate. I would love to see objective research into the topic, if someone were offering it, but not trite dismissals that imply Google Translate is somehow immune to hallucinations.
Sure, in translation one always has issues of sarcasm or irony, but I felt the tool was probably hallucinating more than being a useful work instrument.
Lagniappe: https://www.youtube.com/watch?v=CFCABnWlN8E
EDIT: and yes, I also prefer the older behaviour of translation programs, whose output was noticeably disfluent where it was poor instead of just bullshitting to stay fluent.
A priori, it seems like a pretty huge issue, because it changes a sentence's meaning to its opposite. Fortunately, it's usually easy to notice. But then again, I obviously wouldn't know about any instances I haven't noticed.
Even something like Halloween, which apparently triggered this discussion, is not something most people, including kids, seem to be particularly familiar with. When I mentioned to a Chinese friend that we were celebrating Halloween last year, she advised me to be careful when inviting ghosts into my home. She was unaware that it is mostly a fun children's holiday where they dress up and get candy.
I'd blamed chinese factories needing more places to sell their plastic halloween gear, but now it sounds like it just comes down to US media saturation?
Then again, we should all be stealing more holidays from each other; a more syncretic world is a less boring one.
[My german teacher in high school said the best thing about growing up in southern germany was that they got all the holidays (both protestant and christian) off from school]
Source: Was fansub translator, partook in many translator flame wars over translation disagreements and we all shook heads at the work of craplators.
Also, I will tell you most professional translators are shit at their job.
I can't wait until computer programs can practically take over translating, it's a thankless sweatshop line of work.
I asked ChatGPT 4o to translate the README: https://chatgpt.com/share/6700bed9-1198-8004-8eed-07f5055d07...
The translation seemed largely consistent with what Google Translate provided, but some of ChatGPT’s translation differences seemed more plausible to me, and it certainly reads more coherently. It also doesn’t keep forgetting that it’s dealing with the proper name of the program.
I didn’t try Gemini for this, but I imagine it has to be decent at translation too, so I wonder if/when Google will use Gemini to assist, replace, or otherwise complement Google Translate.