Reading comprehension based question answering system in Bangla language with transformer-based learning

Tanjim Taharat Aurpa; Richita Khandakar Rifat; Md Shoaib Ahmed; Md Musfique Anwar; A B M Shawkat Ali

doi:10.1016/j.heliyon.2022.e11052

Reading comprehension based question answering system in Bangla language with transformer-based learning

Heliyon. 2022 Oct 12;8(10):e11052. doi: 10.1016/j.heliyon.2022.e11052. eCollection 2022 Oct.

Authors

Tanjim Taharat Aurpa^{1

2}, Richita Khandakar Rifat², Md Shoaib Ahmed³, Md Musfique Anwar², A B M Shawkat Ali^{4

5}

Affiliations

¹ Department of Computer Science and Engineering, International University of Business Agriculture and Technology, Bangladesh.
² Department of Computer Science and Engineering, Jahangirnagar University, Savar, Dhaka, Bangladesh.
³ Brian Station 23 Ltd, Dhaka, Bangladesh.
⁴ Central Queensland University, Melbourne, Australia.
⁵ JU Data Mining Research Lab, Dhaka, Bangladesh.

Abstract

Question answering (QA) system in any language is an assortment of mechanisms for obtaining answers to user questions with various data compositions. Reading comprehension (RC) is one type of composition, and the popularity of this type is increasing day by day in Natural Language Processing (NLP) research area. Some works have been done in several languages, mainly in English. In the Bangla language, neither any dataset available for RC nor any work has been done in the past. In this research work, we develop a question-answering system from RC. For doing this, we construct a dataset containing 3636 reading comprehensions along with questions and answers. We apply a transformer-based deep neural network model to obtain convenient answers to questions based on reading comprehensions precisely and swiftly. We exploit some deep neural network architectures such as LSTM (Long Short-Term Memory), Bi-LSTM (Bidirectional LSTM) with attention, RNN (Recurrent Neural Network), ELECTRA, and BERT (Bidirectional Encoder Representations from Transformers) to our dataset for training. The transformer-based pre-training language architectures BERT and ELECTRA perform more prominently than others from those architectures. Finally, the trained model of BERT performs a satisfactory outcome with 87.78% of testing accuracy and 99% training accuracy, and ELECTRA provides training and testing accuracy of 82.5% and 93%, respectively.

Keywords: Bangla language; Bangla question answering; Bangla reading comprehension; Reading comprehension; Transformer-based learning.