Natural Language Toolkit

from Wikipedia, the free encyclopedia
Natural Language Toolkit
Basic data

developer NLTK development team (originally Steven Bird, Ewan Klein and Edward Loper)
Current  version 3.5
( April 12, 2020 )
operating system cross-platform
programming language python
category Computational linguistics
License Apache 2.0
German speaking Yes
nltk.org

The Natural Language Toolkit ( NLTK ) is a compilation of libraries and programs in the Python programming language (from version 2.6) for applications in computational linguistics . The NLTK is open source and is distributed under the Apache license .

The development of the NLTK began in 2001 at the University of Pennsylvania under Edward Loper and Steven Bird, both of whom have led the project since then together with Ewan Klein. Since NLTK was primarily developed for teaching purposes and was created accordingly, extensive documentation, including an accompanying textbook written by the NLTK developers themselves, on (symbolic as well as statistical) language processing in Python is an integral part of the project. The NLTK was therefore particularly widespread in the teaching area of linguistics or computational linguistics , information retrieval and machine learning as well as cognitive science , but it can and is also used in research.

literature

  • Jacob Perkins: Python Text Processing with NLTK 2.0 Cookbook . Packt Publishing, 2010. ISBN 978-1-849-51360-9
  • Steven Bird, Ewan Klein, Edward Loper: Natural Language Processing with Python . O'Reilly Media, 2009. ISBN 978-0-596-51649-9

Web links

Individual evidence

  1. ↑ Release 3.5 . April 12, 2020 (accessed April 13, 2020).
  2. ↑ The nltk Open Source Project on Open Hub: Languages Page . In: Open Hub . (accessed on October 19, 2018).
  3. ↑ NLTK License
  4. ↑ https://github.com/nltk/nltk/wiki/FAQ
  5. ↑ http://code.google.com/p/nltk/wiki/People
  6. ↑ Bird, Steven; Ewan Klein; Edward Loper (2009): Natural Language Processing with Python , O'Reilly Media Inc., ISBN 0-596-51649-5 .