jonathanb88
Joined 2 years ago
Joined 2 years ago
I expect the app still works well for reinforcing vocabulary, but less well for demonstrating grammar.
The approach I use should work if there are sufficient 'scaleable' ways to improve accuracy and choose the right phrases. Language analysis, NLP, LLMs etc all help here, and there are many methods I can still use and will add over time. I'm very much at a proof of concept stage right now!
This approach won't work if accuracy improvements quickly reach diminishing returns and an explosion of rules and/or human proofing to handle edge cases are required.
I'm hoping for the former!
Optimising the tradeoff between more frequent repetition of vocabulary versus better quality grammar examples is where a lot of the work is.
This is something that will improve over time - as it gets better at identifying longer phrases I can implement rules so it won't omit a neighbouring noun if the phrase contains a verb.
Side-note: A few eBooks are causing errors on the backend that don't appear to be DRM-related. I will prioritise getting this fixed.
Whilst there are some, often amusing, quirks with the LLM based explanations, I agree that the utility of the app is much higher with them.
I will expand the app into more countries once I'm happy none of the books have copyright restrictions there. Feel free to message me with the country you reside in and I'll take a look soon.
I'll look to fix the first tomorrow, and add the rest to my list.