Text classification on Tamil

Abstract

By and large, we don't know to talk and read the territorial dialects that are spoken in our nation. So we have accepted Tamil language as it is our territorial and numerous doesn't get it. In our task, the content in Tamil language is stacked from Wikipedia. It is then sifted through and extraordinary characters are evacuated it is then characterized by the titles like id, title, URL, etc. It is then used to prepare the model utilizing CNN calculation and the dataset is created. Along these lines, you would now be able to test utilizing an irregular Wikipedia page and the content is grouped by the titles and anticipated.