Weka wrapper for the SGM toolkit for text classification and modeling.
Java API for the Romanian WordNet
A proram to de-inflect modern Hebrew words
Lexicon and data model for Elvish languages
WNLT is a suite of open source natural language modules for the Welsh
Dialogue Similarity
A simple vocabulary builder with Unicode support.
Nigerian component of the International Corpus of English
Virastyar is an spell checker for low-resource languages
cross-languages resources
To aid translation of satsangs of Paramhamsa Nithyananda
Drug name extraction
Quran Search Engine
A Lexical Substitution Framework