stanfordnlp/stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

71
/ 100
Verified

This tool helps researchers, linguists, and data analysts understand the structure and meaning within text written in over 60 human languages. You input raw text, and it identifies individual words, breaks text into sentences, recognizes named entities like people or places, and analyzes grammatical relationships. It's particularly useful for those working with large volumes of text who need detailed linguistic annotations.

7,736 stars. Used by 19 other packages. Available on PyPI.

Use this if you need to programmatically analyze text for linguistic features like sentence boundaries, part-of-speech tags, named entities, or grammatical dependencies across many languages, including specialized biomedical or clinical English.

Not ideal if you primarily need high-level sentiment analysis or basic keyword extraction, as its strengths lie in deep linguistic parsing rather than simple text categorization.

linguistic-analysis text-mining biomedical-nlp information-extraction multilingual-data
Maintenance 10 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

7,736

Forks

940

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

10

Reverse dependents

19

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/stanfordnlp/stanza"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.