What it does
TreeTagger annotates words with grammatical tags and lemmas, with language parameter files and a chunking mode for selected languages.
Choose a language parameter file as well as the TreeTagger program and scripts. The tool labels text with word, part-of-speech and, where the selected model provides it, lemma information. Parameter files differ in encoding and coverage; some ancient Greek sets omit lemmas. Unix installation instructions require a path without spaces, while Windows has its own setup guide. The chunker also needs the matching language resources. Free use covers research, education and evaluation; other uses require contacting the developer.
Strengths
- Word, grammatical-tag and lemma output
- Parameter files for multiple languages
Watch out for
- Commercial and other uses need a separate licence
Best for
- Preparing linguistically annotated text for corpus analysis
Sources
- TreeTagger (Oct 26, 2026)
- TreeTagger | Official product and parameter files (Oct 26, 2026)