Skip to main content Skip to secondary navigation

Docket #: S12-307

Stanford CoreNLP


Stanford CoreNLP provides a set of natural language analysis tools which take raw English language text input and provide the base forms of words, their parts of speech (i.e. names of companies, people, normalize dates, times, numeric quantities, etc.) and mark up the structure of sentences in terms of phrases and word dependencies, indicating which noun phrases refer to the same entities. Stanford CoreNLP is an integrated framework, making it very easy to apply multiple language analysis tools to a piece of text. Starting from plain text, all the tools can be run simultaneously with just two lines of code.

Stanford CoreNLP Group's tools:

  • Parser, 05-230
  • Name Entity Recognizer (NER), 05-384
  • Part-of-Speech (POS) Tagger, 08-356
  • Classifier, 09-165
  • Word Segmenter, 09-164
  • Applications

    • CoreNLP and the accompanied suite of tools are appropriate for any application requiring human language technology or natural language processing tools necessary to manage human language text (i.e. text mining, business intelligence, web search, sentiment analysis, natural language understanding, etc.).


    • CoreNLP is designed to be quick, easy, highly flexible and extensible, with single option to enable/disable the various tools.

    Similar Technologies

    Explore similar technologies by keyword: