LINGUIST List 14.2189

Tue Aug 19 2003

Software: NLTK 1.1: Natural Language Processing Software

Editor for this issue: Tomoko Okuno <tomokolinguistlist.org>

Directory

  • Edward Loper, NLTK 1.1: Natural Language Processing Software

    Message 1: NLTK 1.1: Natural Language Processing Software

     Date: Tue, 19 Aug 2003 01:57:57 -0700
    From: Edward Loper <edlopergradient.cis.upenn.edu>
    Subject: NLTK 1.1: Natural Language Processing Software


    NLTK version 1.1 is now available on SourceForge: http://nltk.sourceforge.net

    NLTK, the Natural Language Toolkit, is a suite of Python libraries and programs for symbolic and statistical natural language processing. NLTK includes graphical demonstrations and sample data. It is accompanied by extensive documentation, including tutorials that explain the underlying concepts behind the language processing tasks supported by the toolkit.

    NLTK is ideally suited to students who are learning NLP (natural language processing) or conducting research in NLP or closely related areas, including empirical linguistics, cognitive science, artificial intelligence, information retrieval, and machine learning. NLTK has been used successfully as a teaching tool, as an individual study tool, and as a platform for prototyping and building research systems.

    NLTK version 1.1 adds: - A new package containing 11 datasets that are useful for developing and testing NLP tools, along with tokenizers and parsers to provide a high-level interface to the datasets. - A new package containing third party contributions to NLTK that have not (yet) been incorporated into the toolkit. - Significant improvements to the documentation, including new tutorials, revised tutorials, and improved API documentation. - A new module that defines a standard interface for stemmers, and implements the Porter stemmer. - Improvements to the graphical demos.

    For a complete list of improvements, see the change log: http://sourceforge.net/project/shownotes.php?release_id=178889