Stanford NLP Group: Stanford Word Segmenter

Last Updated: 10/2/2012 12:00:00 AM
Site: http://nlp.stanford.edu/software/segmenter.shtml

Stanford Word Segmenter is a free, open source Java-based tokenization tool for Chinese and Arabic text that integrates token pre-processing, or segmentation. For Arabic, the tool processes text according to the Penn Arabic Treebank 3 standard. For Chinese, users can choose between the Chinese Penn Treebank or Peking University standards.

Documentation

Creator(s): Stanford Natural Language Processing Group

Creator's Site: http://nlp.stanford.edu/

Creator's Email:

Repository:

Attributes

Type of analysis: Natural Language Processing Analysis Content Analysis
Type of license: Free Open Source
Web Usable: Software you Download and Install
Ease of Use: Difficult
Tool Family: Stanford NLP
TaDiRAH Goals: Analysis
TaDiRAH Methods: Content Analysis

List this tool appear on

Comments

Rating

Suggested Tools