What is new?
The Text Categorization tool 2011 version is the 5th official public release.
It was developed in pure Java, capable of handling UTF-8. Bellows are some specifications of this tool.
System
- Upgrade to Java 1.6.0.21
- Upgrade to HSqlDb 2.0.0
- Provides scripts for command line tools
Data
- Used MEDLINE.2011 for citations created in years of 2008, 2009, 2010
- Used Metathesaurus.2010AB
- Used lsi2011.xml
- Used the latest data set for JDI, STI, and STRI
- Updated the default value of Mac. normalized count
- Compatible to run with data set of:
- tcData.2010
- tcData.2009
- tcData.2008
- tcData.2007
Features
- Add new features in StWsd to take ST abbreviations and TUI as St candidates