The Stanford Alpaca project presents a replicable instruction-following language model and its research materials.
CoreNLP
Stanford CoreNLP provides natural language analysis tools that process raw text into linguistic annotations.
About CoreNLP
Stanford CoreNLP is a suite of natural language analysis tools that takes raw text and produces linguistic annotations. It can return base forms of words, parts of speech, recognize names of companies and people, normalize dates, times and numeric quantities, mark sentence structure in terms of phrases and word dependencies, indicate which noun phrases refer to the same entities, and indicate sentiment. It integrates several Stanford NLP tools, including the part-of-speech tagger, named entity recognizer, parser, coreference resolution system, sentiment analysis, and bootstrapped pattern learning tools.
The framework is written in Java and is designed so the whole set of tools can be applied with two lines of code, with a single option controlling which tools are enabled or disabled. The basic distribution provides model files for English; the engine is compatible with models for other languages, with packaged models for Chinese and Spanish, and German and Arabic models usable inside CoreNLP. The download is 260 MB and requires Java 1.8+. It is licensed under the GNU General Public License v3 or later, which allows many free uses but not use in proprietary software distributed to others. Source is included.
Key features
- Tokenization, sentence splitting, part-of-speech tagging and lemmatization
- Named entity recognition, syntactic parsing and coreference resolution
- Sentiment analysis and SUTime normalization of dates and numeric quantities
- Single annotators setting enables or disables individual analysis tools
- English models included; packaged Chinese and Spanish models, German and Arabic usable
- Java library with Maven artifacts; runs from a command line or properties file
Best for: Researchers and developers who need to run multiple linguistic annotations over raw text and can work within a GPL-licensed Java framework.
Good for
- Integrates several NLP tools in one framework applicable with two lines of code
- Source is included and models are provided for several languages
- Highly flexible and extensible, with tools toggled by a single option
Watch out for
- The full GPL permits many free uses but not use in proprietary software distributed to others
- The download is 260 MB and requires Java 1.8+
- Maven releases are made several days after the website release
CoreNLP at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
CoreNLP alternatives
Tools and sites you could use instead, ranked by how closely they match.
The Stanford AI Index gathers data about artificial intelligence for researchers, policymakers, journalists, and the public.
Use SmolVLA, a vision-language-action model trained on data from the LeRobot community, for robotics research.
Falcon LLM is described as a generative language model from the Technology Innovation Institute for a range of AI applications.
Code and documentation to train Stanford's Alpaca models, and generate the data.
Open source
24 alternativesMuse is a text-to-image model that also supports editing images through its generative transformer approach.
Popular in Models & ML Research
Well-known listings from the same topic.
ERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comStable Diffusionhuggingface.co/CompVis/stable-diffusion-v1-4
CoreNLP FAQ
What license does Stanford CoreNLP use?
It is licensed under the GNU General Public License v3 or later. Stanford NLP code is generally GPL v2+, but CoreNLP uses several Apache-licensed libraries, so the composite is v3+. This allows many free uses but not use in proprietary software distributed to others.
Which languages are supported?
The basic distribution provides model files for English analysis. The engine is compatible with models for other languages, with packaged models for Chinese and Spanish, and Stanford NLP models for German and Arabic usable inside CoreNLP.
What is needed to run it?
The download is 260 MB and requires Java 1.8+. Usage normally starts from a Java Properties configuration file whose annotators property lists the tools to enable, though one or two properties can be set on the command line instead.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.