Skip to main content

Stanza

Stanford's open-source NLP toolkit for multilingual text processing, tokenisation and syntactic parsing.

Main category
Language checking
Cost
See the official site for cost
Licence type
Open source
Platforms
Windows / macOS / Linux
Visit Stanza Code repository

Version-watched: add it to favourites and confirmed new releases will show on your favourites page (stored in this browser only).

Details

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.

How it differs from spaCy: Stanza comes from the Stanford NLP Group, offers pretrained neural models for many languages, follows the Universal Dependencies annotation scheme and can also call the Java CoreNLP. spaCy concentrates more on turning the processing pipeline into a customisable, deployable program.

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.