[flagged]
Yeah let's start doing things like they do it in the US perhaps we can end up like them!
EuroLLM: LLM made in Europe built to support all 24 official EU languages
471–480 of 629 posts
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#472For those curious, the 24 official languages are Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, and Swedish. Maltese, interestingly, is the only Afro-Asiatic derived language. Hungarian, Finnish, and Estonian are the three Uralic languages. All the others ar…
> Greek being the only Hellenic one Are there really any other Hellenic languages besides Greek?
Cappadocian Greek is Greek heavily mixed with Turkish, to the extent that is arguably better viewed as a distinct Hellenic language rather than just a nonstandard Greek dialect. However, around a century ago, most Greek speakers were expelled from Turkey and deported to Greece (and the same happened in reverse, most Turkish-speakers in Greece were deported to Turkey), including almost all Cappadocian-speakers - and they and their descendants largely switched to standard modern Greek - with the result that it was long believed that Cappadocian had died out in the 1960s, although more recently it has been discovered that there remain small populations of Cappadocians in rural Greece keeping the language alive.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#473Earlier quoted context omitted.
Maltese isn’t an Arabic dialect. Yes, the grammar and phonology and core function words derive from Arabic, but more than half of the vocabulary comes from Italian/Sicilian-North African Arabic may borrow a few words from Italian here and there (just like English does), but not >50% of their vocabulary.
By your reasoning, English isn't a Germanic language since over half of its vocabulary comes from Latin or French.
You certainly wouldn’t call English a “dialect”
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#474Earlier quoted context omitted.
Well, this was 4 days ago, Spain in talks with Germany regarding the addition of official languages: https://www.politico.eu/article/catalan-basque-galician-boos...
If you can't find a common language within your own country, you shouldn't get to be one country.
I guess you are siding with the Catalans that want to be an independent country, then.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#475Earlier quoted context omitted.
The above is not a discovery though. My experience with government funding is that they apply something and won't even try to sell it because selling is hard: you don't want to know that the thing you built is lacking nor that the competition is better. Especially the academic types don't. Yet I'm paying for these guys. Also, by funding the academics they won't even need to go to the job market.. But as I paid for th…
Much of the neural network work was funded by Canadian Universities, and commercialized by US companies. Even if you look just at the "Attention is all you need" paper, which is primarily by authors working at Google, most of those authors come from academia and are immigrants. Vaswani is an Indian born computer scientist, Shazeer is US, Parmar was born in India, Uszkoreit was born in Germany, Jones was born in the U…
Right, but EU doesn't fund only research but something that (IMO) should be entirely commercial.
To be clear, I don't oppose publicly funded education (nor immigrant academics, though I don't see how this relates?). What I do oppose EU trying to compete with tech giants as if they could - the incentives are not set up right, they won't succeed and the funds will be wasted.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#476Earlier quoted context omitted.
No, that's not how training works. It's not just about having an example in a given language, but also how many examples and the ratio of examples compared to other languages. English hugely eclipses any other language on most US models and that's why performance on other languages is subpar compared to performance on english.
I have never noticed any major difference in performance of ChatGPT between English and Spanish. The truth is that as long as the amount of training data of a given language is above some threshold, knowledge transfers between languages.
The issue starts, when an LLM's transfers knowledge between languages, even though that knowledge is not correct in that language. I have seen this with e.g. ChatGPT answers regarding laws for example where it refers to US laws when asked in German, which are obviously not relevant.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#477Earlier quoted context omitted.
I have never noticed any major difference in performance of ChatGPT between English and Spanish. The truth is that as long as the amount of training data of a given language is above some threshold, knowledge transfers between languages.
The issue starts, when an LLM's transfers knowledge between languages, even though that knowledge is not correct in that language. I have seen this with e.g. ChatGPT answers regarding laws for example where it refers to US laws when asked in German, which are obviously not relevant.
> The issue starts, when an LLM's transfers knowledge between languages, even though that knowledge is not correct in that language. I have seen this with e.g. ChatGPT answers regarding laws for example where it refers to US laws when asked in German, which are obviously not relevant.
There is no necessary correlation between language and the correct set of laws to reference. The language of the question (or the answer, if for some reason they are not the same) is an orthogonal issue to the intended scope. There is no reason US laws couldn't be the relevant to a question asked in German (and, conversely, no reason US laws couldn't be wrong for a question asked in English, even if it was specifically and distinguishably US English.)
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#478Earlier quoted context omitted.
> Maltese, interestingly, is the only Afro-Asiatic derived language. It's Semitic, to be precise. https://en.wikipedia.org/wiki/Semitic_languages
Arabic, even. An outlier, as it is AFAIK the only arabic dialect that is not written with the arabic alphabet. Also it's far removed from other arabic dialects.
Oh, stop it! What are you really trying to say? 'The same language' is usually just a desguised nationalistic claim. Ask yourself: what is the advantage of a language over a dialect or vice versa? Why are you fighting for it (or against it)?
Linguistically, it does not matter -- there is no objective definition of the difference between a language, a dialect, or whatever -lect.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#479No github link, high performance claim with 0 numbers. No technical details. 0 interesting link to learn more. But hey a key people page is there so that's ok.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#480Earlier quoted context omitted.
It's more than political. In speaking Flemish is to Dutch as UK English is to US English. In writing however there is no difference in spelling, but there is a difference in word choice. Now, being from Belgium, even within that small part of the country where everybody is supposed to speak Dutch, I genuinely don't understand people from near the coast, which was about 150 miles from where I used to live.
Are you saying UK and US speak a different language? No one doubts it’s a different dialect, but we are talking about languages.
that is a political distinction