Practical AI Practical AI #78

NLP for the world's 7000+ languages

Expanding AI technology to the local languages of emerging markets presents huge challenges. Good data is scarce or non-existent. Users often have bandwidth or connectivity issues. Existing platforms target only a small number of high-resource languages.

Our own Daniel Whitenack (data scientist at SIL International) and Dan Jeffries (from Pachyderm) discuss how these and related problems will only be solved when AI technology and resources from industry are combined with linguistic expertise from those on the ground working with local language communities. They have illustrated this approach as they work on pushing voice technology into emerging markets.


Discussion

Sign in or Join to comment or subscribe

2020-02-28T22:29:20Z ago

Hi everyone,
My name is Kevin AGBASSO from Benin west africa. I came accross your poadcast today and I loved it. It’s been three years now i set up a business to promote educational games in our local languages. The idea came from the fact that i discovered almost seventy percent of our population could not speak french because they have never been to school. I realized that i was also unrooted in my culture and illetrate in my mother tongue. It became serious when during some family gatherings i was just speechless avoiding to sound gibberish .
I am currently working on a scrabble project to encourage people to learn by entertaining. I developed a prototype in four languages for the time being but the physical production is a challenge because there is not a local manufacturer available. I have been trying an app but my knowledge of python and android is still limited. I did a lot of research and SIL documentation have been helpful in developping the game in Aja, Saxwe and mina language.
I am available to work with you guys to make my dreams come true.
Regards.
Kev
senoumabou@gmail.com
229 98 99 93 55
Cotonou BENIN

0:00 / 0:00