Text Classfication Using CNN and CNN-LSTM

Abstract

Text classification, language modelling, and machine translation are some of the applications. CNNs excel at retrieving local and position-invariant characteristics, but RNNs excel at classification based on a long-range semantic dependency instead of local key-value pairs. It shows out that CNNs perform admirably when used to NLP problems. The basic (Bow) model is a clear oversimplified based on faulty beliefs, but it has been the usual technique for years and has produced reasonable accuracy. The speed of CNNs is a major selling point. In this paper, Text classification is carried out by using a deep learning model that is CNN and a hybrid model using CNN-LSTM and compare the performance of two models.