euagendas / m3inference

A deep learning system for demographic inference (gender, age, and individual/person) that was trained on massive Twitter dataset using profile images, screen names, names, and biographies
http://www.euagendas.org
GNU Affero General Public License v3.0
145 stars 57 forks source link

Support Different Languages Outside the EU? #19

Closed swicaksono closed 3 years ago

swicaksono commented 3 years ago

Hey, thank you for making this project. What awesome and incredible research. Is the project is also supported in different languages outside the EU? If not, which part of the project can emphasize this. I am interested to research this project.

zijwang commented 3 years ago

Hi @swicaksono ! Our focus is languages in EU and, at this moment, we have no plan to expand it to other languages.

computermacgyver commented 3 years ago

Thanks @swicaksono for reaching out. Just a quick note that while we focused on "the 32 most spoken languages in Europe," this includes Arabic and many languages beyond the EU. The research project that funded this was focused on the EU, and while I am passionate about broader cross-language support (currently doing a lot of work with various Indian languages) we don't have the funding to expand m3 at present.

The full list of languages supported is: ar - Arabic bg - Bulgarian bs - Bosnian cs - Czech cy - Welsh da - Danish de - German el - Greek en - English es - Spanish et - Estonian eu - Basque fi - Finnish fr - French ga - Irish hr - Croatian hu - Hungarian is - Icelandic it - Italian lt - Lithuanian lv - Latvian mt - Maltese nl - Dutch no - Norwegian pl - Polish pt - Portuguese rm - Romansh ro - Romanian ru - Russian sk - Slovak sl - Slovenian tr - Turkish un - Unknown