TreeTagger for Java (TT4J) is a Java wrapper around the popular TreeTagger package by Helmut Schmid, a language independent part-of-speech tagger and lemmatizer. It was written with a focus on platform-independence and easy integration into applications.
| Tags | Java Natural Language Processing Library wrapper POS lemmatizer chunker |
|---|---|
| Licenses | LGPL |
| Operating Systems | Java Runtime Environment |
| Implementation | Java 5+ |
Recent releases


Release Notes: This release adds support for reading TreeTagger model files and extracting tagset, lemma, and token dictionaries.


Release Notes: This release supports getting multiple tags/lemmas per token and their probabilities (requires a recent TreeTagger) and improves parsing of TreeTagger output.


Release Notes: The default flush sequence was changed to work with the TreeTagger model for Chinese.