Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AMÁLIA and the future of European Portuguese LLMs

duarteocarmo.com

Post reply on HN
Print view View original

81–90 of 90 posts

Re: AMÁLIA and the future of European Portuguese LLMs

#81

Post by embedding-shape »

pjmlp wrote: post #78
embedding-shape wrote: post #10

Earlier quoted context omitted.

I don't think so, Portugal the country might be small, with a small population, but there is ~250 million "Lusophones" (native Portuguese speakers), making it the fifth-most spoken native language in the world, I'd hardly call that small :) And before everyone screams; yes, European Portuguese is different from Brazilian Portuguese, but they're still both Portuguese and understand each other, so it's not like the tex…

You're missing African Portuguese.

If we're being pedantic, I missed a ton of Portuguese variants :) From the top of my head, at least Macanese Portuguese is missing too, but probably only remember that because I heard it in person recently.

Re: AMÁLIA and the future of European Portuguese LLMs

#82

Post by vova_hn2 »

mcyc wrote: post #52
vova_hn2 wrote: post #49

Earlier quoted context omitted.

I'm not arguing with the rest of your points, but... > Just fine tune the open source Kimi 2.6 with an open source Portuguese dataset I think that tokenizers of all popular models are heavily biased towards English or English and Mandarin. And I don't think that it is possibple to replace the tokenizer without full retraining.

You are right about most tokenizers being heavily biased towards English, but the situation is not so bad for Portuguese. Here are some results on the Goldfish corpus [1] with a few different tokenizers. This measures #characters in corpus / #subwords in tokenized corpus. ``` Llama3 english, 0.216 portuguese, 0.285 italian, 0.287 greek, 0.592 ``` ``` Gemma4 english, 0.219 portuguese, 0.246 italian, 0.249 greek, 0.537…

> tokenizer transfer allows for extending/modifying a tokenizer without retraining the model from scratch.

This is very interesting, I didn't know that! Thanks for the links!

Re: AMÁLIA and the future of European Portuguese LLMs

#83

Post by pjmlp »

embedding-shape wrote: post #81
pjmlp wrote: post #78

Earlier quoted context omitted.

You're missing African Portuguese.

If we're being pedantic, I missed a ton of Portuguese variants :) From the top of my head, at least Macanese Portuguese is missing too, but probably only remember that because I heard it in person recently.

Yes, and Timor Leste as well. :)

Re: AMÁLIA and the future of European Portuguese LLMs

#86

Post by guilhas »

Amazing. Every country should have a foothold on AI, as it will have impact every area of a citizen's life

Quite cheap compared with most public spendings

Europe countries already produce very little. Let's not let the wave pass and end up in a future where Europe is continuously reliant on US and Chinese tech as usual. And their definitions of what truth is

Re: AMÁLIA and the future of European Portuguese LLMs

#87

Post by philipwhiuk »

augusto-moura wrote: post #33
philipwhiuk wrote: post #22

Earlier quoted context omitted.

> I don't necessarily personally feel like preserving European Portuguese in amber is a worthwhile goal (anymore than it is productive for Brits to be prickly about the meteoric rise of US English). That's easy to say when you're not on the other end of US defaultism.

To be fair, it is only natural: Portuguese itself only came to be because the Roman Empire conquered the Lusitan land [1], a lot of English comes from Norman French from the Norman conquest [2], the Americas didn't speak European languages until 500 years ago or so, etc. If you give enough time, all languages will change, and some of them because of major political changes/conquests [1]: https://en.wikipedia.org/wiki…

It's natural to die during childbirth or because the sabretooth tiger nearby thought you looked like an easy target.

Natural doesn't mean good.

Re: AMÁLIA and the future of European Portuguese LLMs

#88

Post by augusto-moura »

philipwhiuk wrote: post #87
augusto-moura wrote: post #33

Earlier quoted context omitted.

To be fair, it is only natural: Portuguese itself only came to be because the Roman Empire conquered the Lusitan land [1], a lot of English comes from Norman French from the Norman conquest [2], the Americas didn't speak European languages until 500 years ago or so, etc. If you give enough time, all languages will change, and some of them because of major political changes/conquests [1]: https://en.wikipedia.org/wiki…

It's natural to die during childbirth or because the sabretooth tiger nearby thought you looked like an easy target. Natural doesn't mean good.

I'm not saying that is good nor that is bad, looking through the anthropology lens there's no value judgement.

Besides, differently from your shocking examples, cultures and languages don't "die" as you seem to imply, they evolve, and that part is natural and not bad or good. Portuguese (and English) will change we liking it or not

Re: AMÁLIA and the future of European Portuguese LLMs

#89

Post by CrimsonRain »

lmf4lol wrote: post #37
CrimsonRain wrote: post #35

Earlier quoted context omitted.

Europe always has a thing for their languages. They think many languages make them stronger while spending billions in system loss due to communication barriers. It is obvious they will try to do the same with LLMs and call it the next best thing since bread and butter. I went to JCON EUROPE this year. The amount of "Europe this" "Europe that" "sovereign this, sovereign that" is mind boggling and just a waste of time…

whats your suggestion? we just eradicate all of our culture and languages and go full on english ? whats wrong with exploring ways to keep national languages alive in the LLM area

Others said a lot already. But yes, go full on English for all official and business needs. Endure a few years of hardship and everyone will come out stronger. Europe can attract so much top talents over night just by this one single step and also save an insane amount of money/resources that can be directed elsewhere.

Re: AMÁLIA and the future of European Portuguese LLMs

#90

Post by algoth1 »

kinow wrote: post #56
algoth1 wrote: post #12

Wouldnt it be easier to fine tune a model to convert the Brazilian Portuguese corpus into European Portuguese and then use that corpus?

That idea is different than what most are talking here in other comments. The grammar and vocabularies don't match, but I think the worst are the expressions. Both sides have *a lot* of expressions that vary per context and location.

I’m a native Portuguese speaker, whom grow up watching morning Brazilian Portuguese cartoons. I would say it’s doable
Post reply on HN