Code and corpus for Indian language computation
This page contatins codes and corpora for morphological segmentation of Dravidian Languages. At first we have, Kannada, Malaylam, Telugu and Tamil. All the corpora is extracted from Amrita University, IIIT-H, IIIT-M Kerala implemented morphological analysers. It also contains cleaned Wikipidieda text for Kannada, Malaylam, Telugu and Tamil. As Github doesn't allow to include files that are bigger than 25 MB. We only upload the models.
For the entire corpus and codes, please contact - Arun - akallararajappan@\uoc.edu