stanfordnlp/CoreNLP

Health v2 · maintenance only

Adoption not part of the score

10102 stars · 2717 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Stanford CoreNLP is a Java suite of natural language processing tools that annotates raw text with tokenization, POS tags, named entities, parses, coreference, and sentiment. It provides an integrated pipeline supporting eight languages and is widely used in academia and industry.

Use cases

• extract named entities from text
• run sentiment analysis on sentences
• parse sentence syntax and dependency structure
• resolve coreferences across a document
• tokenize and segment sentences in text
• build an NLP annotation pipeline in Java
• analyze multilingual text

When to choose

• you need a mature, well-tested suite of classical NLP annotations in Java
• you want a single pipeline covering tokenization through coreference
• you need multilingual support across eight languages
• you prefer rule-based or lightweight models over large transformer models

When to avoid

• you need state-of-the-art transformer-based NLP accuracy
• your project is proprietary and cannot comply with GPL licensing
• you work primarily in Python and prefer spaCy or Stanza
• you need languages beyond the eight supported ones

Facets

library · maturity stable

nlp parser machine-learning machine-learning developer-tools jvm cross-platform named-entity-recognition coreference-resolution sentiment-analysis tokenization dependency-parsing part-of-speech-tagging java pipeline multilingual natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="stanfordnlp/CoreNLP")