Stanford NLP Software for .NET

The Stanford NLP Group makes parts of Natural Language Processing software available to everyone. These are statistical NLP toolkits for various major computational linguistics problems. They can be incorporated into applications with human language technology needs.

Getting started

  • Choose the package that is the most suitable for your task. If your task is complex and you need a deep analysis - select Stanford CoreNLP.
  • Install selected NuGet package.
  • Download original ZIP archive for selected package from The Stanford NLP Group site. (Direct links are mentioned on the packages pages)
  • Unzip *.jar file with models if such one exists.
  • You are ready to start, please look at examples.

Note: Do not try to reference several NuGet packages from your solution. They are incompatible with each other. If you need more than one - you should reference Stanford CoreNLP package. All features are packed inside.

If you want to speed up the conversion of some new Stanford software or you want to see new .NET samples for already existing distributions - please mention this in issues. It can really help you get it sooner.

Supported software distributions

All these software distributions are open source, licensed under the GNU General Public License (v2 or later). Note that this is the full GPL, which allows many free uses, but does not allow its incorporation into any type of distributed proprietary software, even in part or in translation. Commercial licensing is also available; please contact The Stanford Natural Language Processing Group if you are interested.

Stanford CoreNLP

An integrated suite of natural language processing tools for English and (mainland) Chinese, including tokenization, part-of-speech tagging, named entity recognition, parsing, and coreference.
See also: Online CoreNLP demo.

View details »

Stanford Parser

Implementations of probabilistic natural language parsers: highly optimized PCFG and dependency parsers, a lexicalized PCFG parser, and a deep learning reranker.
See also: Online parser demo and the Stanford Dependencies page.

View details »

Stanford POS Tagger

A maximum-entropy (CMM) part-of-speech (POS) tagger for English, Arabic, Chinese, French, and German.

View details »

Stanford Named Entity Recognizer

A Conditional Random Field sequence model, together with well-engineered features for Named Entity Recognition in English, Chinese, and German.
See also: Online NER demo

View details »

Stanford Word Segmenter

A CRF-based word segmenter. Supports Arabic and Chinese.

View details »

Stanford Temporal Tagger (SUTime)

A rule-based temporal tagger for English text.
See also: Online SUTime demo

View details »


The project is hosted on GitHub where you can report issues, fork the project and submit pull requests. You might also want to read library notes to understand how it works.

Fork me on GitHub