Feature Extraction Using Deep Generative Models for Bangla Text Classification on a New Comprehensive Dataset
This work addresses the scarcity of text datasets for Bangla, the sixth most widely spoken language, by providing a new dataset and applying computer vision-inspired methods, though it is incremental in adapting existing models to a new domain.
The authors tackled the problem of Bangla text classification by creating a new comprehensive dataset of 212,184 documents and using deep generative models for feature extraction, finding that the adversarial autoencoder model produced the best feature space for classification.
The selection of features for text classification is a fundamental task in text mining and information retrieval. Despite being the sixth most widely spoken language in the world, Bangla has received little attention due to the scarcity of text datasets. In this research, we collected, annotated, and prepared a comprehensive dataset of 212,184 Bangla documents in seven different categories and made it publicly accessible. We implemented three deep learning generative models: LSTM variational autoencoder (LSTM VAE), auxiliary classifier generative adversarial network (AC-GAN), and adversarial autoencoder (AAE) to extract text features, although their applications are initially found in the field of computer vision. We utilized our dataset to train these three models and used the feature space obtained in the document classification task. We evaluated the performance of the classifiers and found that the adversarial autoencoder model produced the best feature space.