Enhancing Deep Learning Approach for Tamil English Mixed Text Classification
Neeraj Bhargava, Anantika Johari · Advances in computer science research · 2023
Text Classification with sentiments understanding is an essential task for data processing and predicting user behavior.In case of Multilingual data, the process requires to convert the entire data to machine understandable language or to pre-process the text prior to classification keeping the semantics of the text intact.Deep Learning libraries like Bidirectional Encoder Representations from Transformers (BERT) with word2vector model and Convolutional Neural Network (CNN) for natural language processing (NLP) support both techniques, and the manuscript attempts to enhance pre-processing of the Tamil English Mixed text Classification.The pre-processing of the Tamil English Mixed text addressed the issue of annotated text non-availability.