Researcher in cognitive linguistics, comparative linguistics, and corpus linguistics. I build tools and systems for language researchers, educators, and learners.
Apps
- Monadic Chat -- Locally hosted AI chatbot platform on Docker (Mac/Win/Linux)
- SpeechDock -- Mac menu bar app for speech-to-text with system audio capture, live subtitles, and translation
Web Services
- TED Corpus Search Engine -- Full-text search across TED Talk transcripts
- RSyntaxTree -- Syntax tree diagram generator for linguists
- Paradocs -- Paragraph-oriented document presentation with sentence-level highlighting and TTS
- jReadability.net -- Japanese text readability measurement and learning tools
Libraries and CLI Tools
- ruby-spacy -- Ruby wrapper for the spaCy NLP library
- WP2TXT -- Wikipedia dump to plain text converter
- Code Packager -- Package a codebase into a single JSON file for LLM analysis
- EngTagger / Lemmatizer -- English POS tagger and lemmatizer (Rubygems)
I write about my projects, linguistics, and other interests at yohasebe.com.



