The Stanford Parser can be used to generate constituency and dependency parses of sentences for a variety of languages. The package includes PCFG, Shift Reduce, and Neural Dependency parsers. To fully utilize the parser, also make sure to download the models jar for the specific language you are interested in. Links to models jars provided below in History section or here.

Download Stanford Parser 4.2.1

You can consult this legacy FAQ for more info.


You can see demonstrations of the various parsers here.

Differences between Standalone and CoreNLP

If you are using Stanford NLP software for non-commercial purposes, you should use the full CoreNLP package.

Parsing requires tokenization and in some cases part-of-speech tagging. The Stanford Parser distribution includes English tokenization, but does not provide tokenization used for French, German, and Spanish. Access to that tokenization requires using the full CoreNLP package. Likewise usage of the part-of-speech tagging models requires the license for the Stanford POS tagger or full CoreNLP distribution.


The parser code is dual licensed (in a similar manner to MySQL, etc.). Open source licensing is under the full GPL, which allows many free uses. For distributors of proprietary software, commercial licensing is available. (Fine print: The traditional (dynamic programmed) Stanford Parser does part-of-speech tagging as it works, but the newer constituency and neural network dependency shift-reduce parsers require pre-tagged input. For convenience, we include the part-of-speech tagger code, but not models with the parser download. However, if you want to use these parsers under a commercial license, then you need a license to both the Stanford Parser and the Stanford POS tagger. Or you can get the whole bundle of Stanford CoreNLP.) If you don’t need a commercial license, but would like to support maintenance of these tools, we welcome gift funding: use this form and write “Stanford NLP Group open source software” in the Special Instructions.


VersionDate          ChangesModels
4.2.12020-05-05Reduce size of srparser modelsarabic, chinese , english , english (kbp), french , german , spanish
4.2.02020-11-17Retrain English models with treebank fixesarabic, chinese , english , english (kbp), french , german , spanish
4.0.02020-04-19Model tokenization updated to UDv2.0arabic, chinese , english , english (kbp), french , german , spanish
3.9.22018-10-17Updated for compatibilityarabic, chinese , english , english (kbp), french , german , spanish
3.9.12018-02-27new French and Spanish UD models, misc. UD enhancements, bug fixesarabic, chinese , english , english (kbp), french , german , spanish
3.8.02017-06-09Updated for compatibilityarabic, chinese , english , english (kbp), french , german , spanish
3.7.02016-10-31new UD modelsarabic, chinese , english , english (kbp), french , german , spanish
3.6.02015-12-09Updated for compatibilitychinese , english , french , german , spanish
3.5.22015-04-20Switch to universal dependenciescaseless , chinese , shift reduce parser , spanish
3.5.02014-10-31Upgrade to Java 8; add neural-network dependency parsercaseless , chinese , shift reduce parser , spanish
3.4.12014-08-27Spanish models added.caseless , chinese , shift reduce parser , spanish
3.42014-06-16Shift-reduce parser, dependency improvements, French parser uses CC tagsetcaseless , chinese , shift reduce parser
3.3.12014-01-04English dependency “infmod” and “partmod” combined into “vmod”, other minor dependency improvements 
3.3.02013-11-12English dependency “attr” removed, other dependency improvements, imperative training data added 
3.2.02013-06-20New CVG based English model with higher accuracy 
2.0.52013-04-05Dependency improvements, -nthreads option, ctb7 model 
2.0.42012-11-12Improved dependency code extraction efficiency, other dependency changes 
2.0.32012-07-09Minor bug fixes 
2.0.22012-05-22Some models now support training with extra tagged, non-tree data 
2.0.12012-03-09Caseless English model included, bugfix for enforced tags 
1.6.92011-09-14Improved recognition of imperatives, dependencies now explicitely include a root, parser knows osprey is a noun 
1.6.82011-08-04New French model, improved foreign language models, bug fixes 
1.6.72011-05-18Minor bug fixes. 
1.6.62011-04-20Internal code and API changes (ArrayLists rather than Sentence; use of CoreLabel objects) to match tagger and CoreNLP. 
1.6.52010-11-30Further improvements to English Stanford Dependencies and other minor changes 
1.6.42010-08-20More minor bug fixes and improvements to English Stanford Dependencies and question parsing 
1.6.32010-07-09Improvements to English Stanford Dependencies and question parsing, minor bug fixes 
1.6.22010-02-26Improvements to Arabic parser models, and to English and Chinese Stanford Dependencies 
1.6.12008-10-26Slightly improved Arabic and German parsing, and Stanford Dependencies 
1.62007-08-19Added Arabic, k-best PCCFG parsing; improved English grammatical relations 
1.5.12006-06-11Improved English and Chinese grammatical relations; fixed UTF-8 handling 
1.52005-07-21Added grammatical relations output; fixed bugs introduced in 1.4 
1.42004-03-24Made PCFG faster again (by FSA minimization); added German support 
1.32003-09-06Made parser over twice as fast; added tokenization options 
1.22003-07-20Halved PCFG memory usage; added support for Chinese 
1.12003-03-25Improved parsing speed; included GUI, improved PCFG grammar 
1.02002-12-05Initial release