Speaking as a total ignorant from a coding perspective. But I guess that wouldn’t be the hard part, considering that most of Duolinguo is just boxes and text inputs. How difficult it is to create a database of competent linguists with an efficient training who can progressively enhance your understanding of languages?
The technology is probably the smallest part of the problem. Most of it will be getting it critical mass of users, and expanding that user base, cross multiple languages. So that’s advertising, politics, social networking, promotion.
Yeah and their staff have been very dogged about promotion in language communities, including crowdsourcing the content (i.e. getting their users to produce it for free)
Check out LibreLingo and these
I did know about LibreLingo, but it still feels like it’s taking really small steps! And the other alternatives don’t seem to offer the semi-holistic experience that Duolingo provides.
it doesn’t live up to his expectations while being made by someone else on their free time. This mentality is rampant in opensource.
Is he going to contribute, not likely
is he going to donate so they can work on it, also no
is he going to vaguely ask others to make an app to compete with commercial companies, Oh yesss
Join LibreLingo instead of creating your own scratch. Unless you’re planning to use Rust lol
I think a combination of fast advancements in multilingual open source TTS models and maybe LLMs? could help. The problem is LLMs habitually lie. It also may be unneeded. Duolingo seems relitively simple iirc (2019 was the last time I used it) a combination of simple phrases and good gamification of topics. Add some anxiety and there you go, Duolingo lite or sumthin
As jet said the difficult part is the content, not really the “technology” (which is mostly just flashcards tech + quick “fill the void” exercises, and we already have software like Anki). There’s probably the gamification aspect too.
There are lots of free language learning materials on the internet. For Japanese for example, there’s Tae Kim’s course: https://guidetojapanese.org/learn/ (his grammar guide has a CC BY-SA 3.0 license, his “complete” guide has no license yet as he hasn’t finished it yet). It would be great if course authors could allow open-source devs to build a unifying app on top of their courses (it does seem that Tae Kim is okay with it, since he allowed an Android dev to make an (now discontinued) app version of the course: https://play.google.com/store/apps/details?id=com.alexisblaze.japanese_grammar).
Let’s not overstate Duolingo’s effectiveness for language learning.
The technological challenge to adopting a self-taught language learning method into an app is rather small. You just need the content. Either you develop the course under a Free Culture license, or you purchase the rights for an existing method and you port it. Plus maybe some volunteers to handle user-interaction.
A good example is the VHS Lernportal which implements three levels of German class in a way that actually has some pedagogical merit. It’s killer-feature is nothing technological, but that they have some teachers in the backoffice that will read your occasional text-production exercises and offer corrections (no, language tool wouldn’t be able to replace humans in that case, because language tool doesn’t know what you are trying to say and therefore gives you multiple guesses but no way to know which one you actually need).
