Morphological decomposers for SA Languages (Windows)

For isiNdebele, Siswati, isiXhosa and isiZulu Morph. decomposers.

1.	Input.txt - Input format: Text data (encoding: ASCII/CP1252), one token per line. Saved in decomposer directory.
2.	Morph. decomposer usage (command line): "Script.NCHLT.[Language]Morph.1.0.1.exe"
3.	Output.txt - Morphologically decomposed text output. Structure: "Token tab Analysis". Saved in decomposer directory.

For Sepedi, Setswana, Sesoto, Tshivenda and Xitsonga Morph. decomposers.

1.	Input.txt - Input format: Text data (encoding: UTF8 without BOM), one token per line. Saved in decomposer directory.
2.	Morph. decomposer usage (command line): "Script.NCHLT.[Language]Morph.1.0.1.exe"
3.	Output.txt - Morphologically decomposed text output. Structure: "Token tab Analysis". Saved in decomposer directory.


For Afrikaans Morph. decomposer:

1.	Download the C5.0 classifier interpreter source code at http://rulequest.com/see5-public.tgz (See interpreter documentation for details) 
	and compile using a c++ compiler (e.g. cpp. See compiler documentation for details).
2.	Rename the compiled interpreter to "C5.0Interpreter.exe" and save the file to the \bin directory.
3.	Afrikaans Morph decomposer usage (command line): "Script.NCHLT.AfrikaansMorph.1.0.1.exe"
	Input.txt - Input format: Text data (encoding: ASCII/CP1252), one token per line. Saved in decomposer directory.
4.	Output.txt - Morphologically decomposed text output. Structure: "Token tab Analysis". Saved in decomposer directory.

License

These files are distributed under the Creative Commons Attribution 2.5 South Africa license. 

All files are distributed under the same conditions.
_______________________________________________
License: Creative Commons Attribution 2.5 South Africa
URL: http://creativecommons.org/licenses/by/2.5/za/

Attribute work to: South African Department of Arts and Culture & Centre for Text Technology (CTexT, North-West University, South Africa)

Attribute work to URL: http://www.nwu.ac.za/ctext 
______________________________________________