Docket #: S05-230
Stanford (Statistical Natural Language) Parser
FOR ALL LICENSING INQUIRIES PLEASE EMAIL NLP Licensing.
Researchers in the Stanford Natural Language Processing Group have developed a Java implementation of probabilistic natural language parsers - both lexicalized PCFG parser and highly optimized PCFG and dependency parsers. The parser program provides typed dependencies output as well as phrase structure trees. The software was originally developed for determining the grammatical structure of English sentences and has been adapted to work with other languages, including Chinese, German, Italian and Arabic.
Ongoing Research:
The inventors continue to modify and extend the parser to handle other languages, to support additional features, and to improve performance and flexibility.
Licensing:
The Stanford Parser is available for download for non-commercial use under the GNU GPL at http://nlp.stanford.edu/software/lex-parser.shtml. If you would like a commercial license, please contact Chris Tagge at tagge@stanford.edu or 650-725-8402.
Applications
- Assigning sentence structure to human text:
- languages - English, Chinese, German, Italian and Arabic
- output - typed dependencies or phrase structure trees
Advantages
- Guarantee of exact inference
- Accurate unlexicalized model
Publications
- Dan Klein and Christopher D. Manning. 2003. Fast Exact Inference with a Factored Model for Natural Language Parsing. In Advances in Neural Information Processing Systems 15 (NIPS 2002), Cambridge, MA: MIT Press, pp. 3-10.
- Dan Klein and Christopher D. Manning. 2003. Accurate Unlexicalized Parsing. Proceedings of the 41st Meeting of the Association for Computational Linguistics, pp. 423-430.
- Marie-Catherine de Marneffe, Bill MacCartney, and Christopher D. Manning. 2006. Generating Typed Dependency Parses from Phrase Structure Parses. 5th International Conference on Language Resources and Evaluation (LREC 2006).
Stanford Parser and Inventor Profiles
- Stanford Parser (includes download under GNU GPL)