Vocab extractor for language learners using Stanza and frequency ranks
Details
- External ID
- 47567341
- Source
- HN
- Company
- —
- Product
- Vocab extractor for language learners using Stanza and frequency ranks
- Website domain
- huggingface.co
- Launched
- March 29, 2026
- Cohort
- —
- Upvotes
- 6
- Upvotes percentile
- 0.2853628536285363
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I'm building a Telegram bot to practice Dutch. GPT-4o-mini kept picking vocabulary words I already knew, so I built a classical NLP pipeline to do it instead.It takes a short text + learner level (A0–B1) and returns the best words to study, using Stanza for parsing and corpus frequency ranks (SUBTLEX-NL, srLex, SUBTLEX-US) for scoring. Wins at A1/A2, loses at A0 where the LLM picks more obvious words.I also tried adding multi-word phrases (ADJ+NOUN, VERB+NOUN, phrasal verbs) backed by NPMI-scored collocation whitelists. Couldn't beat GPT there because it just "knows" which phrases matter.For the phrase work I had to extract collocations from 100M+ OpenSubtitles lines. Published them as a free dataset: https://huggingface.co/datasets/vladvlasov256/opensubs-collo... There are 43K bigrams across English, Dutch, and Serbian.Source https://github.com/vladvlasov256/vocab-nlp
Enrichment
- Theme
- AI visibility and marketing tools
- Vertical
- Education
- Function
- Dev tools
- Audience
- B2C
- AI stance
- Not AI
- Project type
- Hobby / open-source project
- Normalized one-liner
- vocabulary extraction for language learners
- Manually corrected
- False
Could you build this?
Yes A small NLP script or Hugging Face Space utilizing existing Python libraries like Stanza and a static frequency list (SUBTLEX) to extract and filter vocabulary is trivial to prompt-engineer.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 55 launches clear the similarity bar, closest 8 shown.
Attention rank: #52 of 56 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 151 days after the earliest competitor.
- SEOBetter · ph · 2026-09-30 · 1 upvotes · similarity 0.44
- ReadPlusOne · hn · 2026-08-25 · 5 upvotes · similarity 0.41
- Turn native language audio into flashcards and shadowing practice · hn · 2026-06-25 · 92 upvotes · similarity 0.40
- Vocab Top · hn · 2026-08-05 · 18 upvotes · similarity 0.40
- Autofit2 · hn · 2026-06-25 · 28 upvotes · similarity 0.39
- SilenVocab · ph · 2026-09-22 · 1 upvotes · similarity 0.38
- I spent 10k hours building the perfect language learning app · hn · 2026-01-15 · 10 upvotes · similarity 0.37
- Learning a Language Using Only Words You Know · hn · 2025-12-15 · 84 upvotes · similarity 0.37
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a dev tools tool for Sales yet.