Vocab extractor for language learners using Stanza and frequency ranks
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…
What it does
In the maker’s words, at launch
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
Does the same job
all alternatives →
- VTVocab Top – AI-powered vocabulary builder that helps you retain wordsAug 2026 · vocab.top · ▲18
- TATake a look at my startup; Show off your vocabulary prowess2011 · ▲25
Hello HN, Introducing VocabGenii.com, my online vocabulary game. It is the first product from my company, Genii, Inc., that brings innovative, engaging new learning experience to the market by leveraging web 2.0 and social networks. Currently, we are running a 10K Challenge -- anyone scoring 10,000 points before the contest ends (March 24 04:00 GMT) will get 3-Month unlimited play. Exceptional performance would also be recognized in our 10K Hall of Fame with limited edition trophies! We're hiring! If you have disruptive ideas on language learning and online education, and possess…
- L3Learn 3 words today with Gemini 1.5 Pro2024 · wordlab.cloud · ▲8
I recently custom prompted 1.5 pro to teach me new words by helping me to make sentences using them - the only way to learn vocab IMO. It's been helpful for my GRE prep, hope you may find it useful as well!
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
