Skip to content

Files

Latest commit

 

History

History
5 lines (3 loc) · 396 Bytes

README.md

File metadata and controls

5 lines (3 loc) · 396 Bytes

Tamil-Murasu-Categorization

Working on categorizing Tamil articles using data from the Tamil Murasu newspaper. The Kaggle Dataset can be found here.

Used the IndicNLP library to tokenise and perform morphological analysis on the corpus.