Indexing and query tools for very large text corpora
Natural Language Processing (NLP) for the Masses
A proram to de-inflect modern Hebrew words
simple BNF parser makes xml markup of matches
C++ Library to hyphenate a text
Offline stemmer for Gujarati , which is one of 22 Indian languages.
A POS, disfluency and multi-word unit annotator for spoken language
Similarity Word-Sequence Kernels for Sentence Clustering toolkit