Learning / Internship Projects & Reports

TextTiling implementation for the NLTK

Name: perrin
Date added: 2010-03-04 15:19:31
Hits: 288
Community Spacehttp://groups.google.com/group/nltk-dev
Link to internship report if online:
Type of learner


NLTK is  the Natural Language ToolKit, a set of tools written in Python, linguistic data and documentation aimed at researchers in natural language processing.

TextTiling is an algorithm produced by Prof. Marti Hearst for subtopic segmentation of full-length text documents. The method takes advantage of the patterns observed by the lexical analysis of the document. This project is an implementation of the TextTiling algorithm in Python for the toolkit

RSS Feeds