NICTA t3as Named-Entity Recognition (NER)

NICTA t3as Named-Entity Recognition is a rule based Named-Entity Recognition library which extracts named entities from text, such as Organisation, Location and Person names. It is written in Java.

Contributed by:

• Mats Henrikson
• William Han
• Scott Sanner
• Kishor Gawande

License

Copyright (c) 2010, National ICT Australia All rights reserved.

This software is under the GPL version 3. Please see the license file LICENSE.txt

The contents (data/documentation/artwork) is under the Creative Commons 3.0 BY-SA More information about "Creative Commons" license can be found at http://creativecommons.org/licenses/by-sa/3.0/

Maven Central

Parts of this project are also available on Maven Central under the org.t3as group id:

http://search.maven.org/#search%7Cga%7C1%7Corg.t3as

Modules

The NICTA NER project contains a number of subprojects implementing various functionality:

1. NICTA NER library This is the core NER library that does the actual processing work. This can be run from the command line or imported into a JVM based project.
2. NER webservice A simple webservice that wraps the NER library.
3. NER client A simple Java client for the remote webservice that can be used either from the command line, or by importing the Java library in your own JVM based projects.
4. NER Web User Interface A simple Haskell/Yesod based demo user interface for the web service.
5. NER Haskell client A client for the web service written in Haskell (which the Yesod web UI makes use of).
6. CoNLL 2003 evaluation Code for carrying out an evaluation of the NER library against the CoNLL 2003 shared task.