12
Learning vocab ahead of reading? (software for epub analysis)
(sh.itjust.works)
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
this post was submitted on 26 May 2026
12 points (92.9% liked)
Language Learning
1009 readers
1 users here now
A community all about learning languages!
Ask / talk about a specific language or language learning in general.
Sopuli's instance rules apply
- Remember the human! (no harassment, threats, etc.)
- No racism or other discrimination
- No Nazis, QAnon or similar whackos and no endorsement of them
- No porn
- No ads or spam
- No content against Finnish law
Other active Lemmy language communities:
- !duolingo@lemmy.world
- !japaneselanguage@sopuli.xyz
- !chinese@lemmy.world
- !learn_finnish@sopuli.xyz
- !german@lemmy.world
- !latin@piefed.social
- !estonian@sopuli.xyz
- !spanish@sopuli.xyz
- !translator@sopuli.xyz (translation studies)
- !esperanto@sopuli.xyz
Other communities outside Lemmy:
Community banner & icon credits:
Icon: The book cover of Babel (2022 novel by R. F. Kuang)
Banner: Epic of Gilgamesh tablet (© The Trustees of the British Museum)
founded 3 years ago
MODERATORS
JPDB.io does something like this for Japanese. Not sure you can really import books, but it basically combines some kind of parser in with a dictionary API, example sentence corpus, and its own spaced repetition system.
Gotta be something along the line out there for most languages, but I can't say I know of the tools. Honestly, the breaking-down-into-a base-word part of it is probably in the dictionary's domain. If you give it a conjugated verb it should usually be able to tell. But then some ambiguities need context, not sure how to account for that.
AnkiConnect lets you tap into the Anki APIs, Wiktionary or (from a quick search) Collins should have a dictionary API available for French-English. If the dictionary APIs are good then you could probably get pretty far with basic sentence parsing.
But yeah, feels like there's gotta be something ready made for it, wish I knew and could point you in a direction.
I've only done enough programming to know this is very possible. A word count is probably all I'd need to do this manualy. Just wondering if this is one of those things I do instead of learning, so the less time I spend on it, the better I'll feel.
Was messing around with Jiten.moe (spiritual successor to jpdb, again boasts the utility of ingesting a book or subtitle file and creating anki cards) and it made me think of this question. (And Jiten is actually open-source, so the repo's there with how they do it... but I'm pretty sure it's mostly just wrapping a bunch of Japanese-specific tools.)
Did a little looking. Tried checking https://github.com/keon/awesome-nlp and didn't see anything French specific, but did come across https://github.com/french-ai/french-nlp which might have useful stuff. It sounds like a library called Spacy could be useful.
But then I ran across this tool, which might be pretty close to what you'd need? https://github.com/FreeLanguageTools/vocabsieve
I haven't looked into exactly how the 'automatically from books' stuff would work or anything, but seems promising.
And I guess elephant in the room, NLP is the kind of task LLMs are actually pretty good at, so there's also always that lazy-ish route: convert the book to text, feed it through an LLM and ask it to identify important vocabulary words.
Thanks! Vocab sieve looks perfect (though experimental), and it works with KOReader, too. Fuck me, I'm running out of excuses.