LINGUIST List 17.2021

Tue Jul 11 2006

Software: Natural Language Toolkit: NLTK-Lite Version 0.6.5

Editor for this issue: Svetlana Aksenova <>

Directory         1.    Steven Bird, Natural Language Toolkit: NLTK-Lite Version 0.6.5

Message 1: Natural Language Toolkit: NLTK-Lite Version 0.6.5
Date: 10-Jul-2006
From: Steven Bird <>
Subject: Natural Language Toolkit: NLTK-Lite Version 0.6.5

NLTK, the Natural Language Toolkit, is a suite of Python libraries and programs for natural language processing. Version 0.6.5 has been released, and can be downloaded from


Software Modules: corpus readers, tokenizers & stemmers, taggers (regexp, n-gram, backoff, Brill, HMM), parsers (recursive descent, shift-reduce, chart, probabilistic, ...), clusterers (EM, k-means, ...), probability distributions, chatbots, demonstrations, ...

Corpora and Corpus Samples: Brown Corpus, CMU Pronunciation Dictionary, CoNNL-2000, Genesis, Gutenberg, IEER, Presidential Addresses, Names, PP-Attachment, Senseval 2, TIMIT, Treebank, Words

Documentation: Tutorials and exercises (190pp), API documentation for all software modules, installation instructions for Windows, Mac, Unix.

ChangeLog for Version 0.6.5 2006-07-09

* Code: - improvements to shoebox module (Stuart Robinson, Greg Aumann) - incorporated feature-based parsing into core NLTK-Lite - corpus reader for Sinica treebank sample - new stemmer package * Contrib: - hole semantics implementation (Peter Wang) - Incorporating yaml - new work on feature structures, unification, lambda calculus - new work on shoebox package (Stuart Robinson, Greg Aumann) * Corpora: - Sinica treebank sample * Tutorials: - expanded discussion throughout, incl: left-recursion, trees, grammars, feature-based grammar, agreement, unification, PCFGs, baseline performance, exercises, improved display of trees

-Steven Bird

Linguistic Field(s): Cognitive Science Computational Linguistics Text/Corpus Linguistics