USING DEEP LEARNING MODELS IN TEXT CLASSIFICATION

Abstract

Text classification is a key task in several areas of natural language processing, including semantic word classification, sentiment analysis, question answering, or dialog management. In this paper, we consider three main types of deep learning architectures for text classification tasks: deep belief neural (DBN), convolutional neural network (CNN), and recurrent neural network (RNN). DBN has excellent learning ability for feature extraction and is suitable for general purposes. CNN is useful for determining the location of different features when RNN is modeled in a long-term relationship sequence.