51–56 of 56 posts
Can translate between 1600 languages. Can't achieve subject-verb agreement in 1st sentence of their English abstract. Advances made through No Language Left Behind (NLLB) have demonstrated that high-quality machine translation (MT) scale to 200 languages.
Advances have demonstrated... The NLLB part is an adjectival(sic) phrase that modifies the noun "Advances".
Hopefully I'm not wrong...
Earlier quoted context omitted.
Hey, this is super cool! I’ve been working on a similar problem, focusing on low-resource and underserved languages including the Mayan family, and have published some research and open resources around that [0, 1]. On the data side, I’ve found that the biggest bottleneck isn’t collecting text (it’s out there!) but reliable language identification. It’s often difficult or ambiguous to separate languages cleanly in da…
You both might find it useful - https://news.ycombinator.com/item?id=44950661 I’ve also recently started in this space: building an agent, for a client, who can communicate in multiple languages.
Can translate between 1600 languages. Can't achieve subject-verb agreement in 1st sentence of their English abstract. Advances made through No Language Left Behind (NLLB) have demonstrated that high-quality machine translation (MT) scale to 200 languages.
Huh? I'm a native English speaker and the sentence looks OK. Advances have demonstrated... The NLLB part is an adjectival(sic) phrase that modifies the noun "Advances". Hopefully I'm not wrong...
Earlier quoted context omitted.
1.6k languages is for how many we were able to find more or less reliable evaluation data (mostly thanks to Bible translators and all those who contributed to BOUQuET). Out of the remaining several thousand languages, we expect the OMT models to support understanding (but not generation) for a significant proportion, due to cross-lingual generalisation between similar languages. So it’s not truly “omni” in the sense…
Is there interest in benchmarking the proprietary LLMs for translation? Curious as I often use Gemini 3 Flash, but I have no idea how good it is for my language family. I prefer open models (in fact the smaller the better for offline), but it'd be useful to know how well the Big Three do.
Earlier quoted context omitted.
Is there interest in benchmarking the proprietary LLMs for translation? Curious as I often use Gemini 3 Flash, but I have no idea how good it is for my language family. I prefer open models (in fact the smaller the better for offline), but it'd be useful to know how well the Big Three do.
We did some benchmarking of them internally, but not sure if we'll publish the detailed results. Just in case, keep an eye on https://huggingface.co/spaces/facebook/bouquet : if we release the evaluation results, they will be there.
Earlier quoted context omitted.
You both might find it useful - https://news.ycombinator.com/item?id=44950661 I’ve also recently started in this space: building an agent, for a client, who can communicate in multiple languages.
Excellent, thank you mandeepj! Curious about the language coverage of your agent and if / how you plan to eval your agent, if you're willing to share more.
evaluating your agent: we are documenting the details, but it should give you some idea about an approach https://news.ycombinator.com/item?id=47232903
Also, you might find this useful - https://open.substack.com/pub/bytebytego/p/how-roblox-uses-a...