Web site: The Stanford Natural Language Processing Group

Date of first review/ name of reviewer: 5/29/08 [Matthew Jockers]

Additional reviewer(s):

Produced by:  The Stanford Natural Language Processing Group

Cost: Free

Description: "A Java implementation of a maximum-entropy (CMM) part-of-speech (POS) tagger."

Platform: Java, Command Line Application

License:The tagger is licensed under the GNU GPL.

Maturity: v1.5

Features:

• Tags Parts of Speech using Penn Treebank Tag set
• Customizable
• Ability to tag XML content (added in v1.5)
• Ability to produce XML results instead of default Penn Treebank

Advantages:

• Comes with several pre-trained models but can easily be retrained
• Full API for Developers
• Simple to set up and install--The system requires Java 1.5+ to be installed.
• Growing user community with an email list

Disadvantages:

• There is a GUI, but it is only for demo purposes. You must be comfortable with the command line to really use this tool

Tips:

• For tagging xml and information about using the tagger with xGrid, See documentation by Matthew Jockers

Tutorials:

• See tips section above

More information: