Stanford's open-source NLP toolkit for multilingual text processing, tokenisation and syntactic parsing.
Stanza is Stanford's open-source natural language processing toolkit supporting multilingual tokenisation, part-of-speech tagging, dependency parsing, named entity recognition and more. It suits linguistics research, text analysis and NLP teaching.
Use cases: NLP, multilingual text processing, tokenisation, syntactic parsing, named entity recognition
Note: Model quality varies by language; for Chinese tasks, compare against spaCy, Transformers and similar tools.
