Compound word splitting for Tamil, Telugu to Hindi SMT


Suffix separation for Agglutinative Indian Languages(Bengali, Marathi, Tamil, Telugu) to Hindi SMT


Reordering system for English to Indian Language Statistical Machine Translation(Updated)


N-fold Cross Validation Script for Statistical Machine Translation


Indian Language Pos-Taggers

	Hindi Postagger 		Marathi Postagger
Bengali Postagger Gujarati Postagger
Konkani Postagger Malayalam Postagger
Telugu Postagger Tamil Postagger
Punjabi Postagger
To run the POS tagger please download required file. You will need to untar the same and execute 'sh sample-input.txt'. You can replace the 'sample-input.txt' with your own file for the POS tagging purpose.

Ranking Translation

	Language model based Ranking Module

Light Weight Stemmer

	LightweightStemmer Hindi
LightweightStemmer Marathi

Indian Language Fonts

	Technology Development for Indian Languages
Indian language Fonts List on Indilinux