Factoid Question Answering over Bangla Comprehension

Question Answering (QA) framework is a data recovery framework in which an explicit reply is required because of a submitted query, as opposed to a lot of references that may contain the appropriate responses. It is a man-machine specialized gadget. The essential thought of QA frameworks in Natural Language Processing (NLP) is to give the right responses to the queries. This paper shows a step towards building a question answering framework in Bangla. A significant initial phase in building up a QA framework is the dataset. As the Bangla QA framework is at the beginning phase of advancement, we have prepared our own Bangla question answering dataset. The proposed model for Bangla-QA contains careful stacking of several deep learning-based sub-models to grasp the context from a comprehension and generate appropriate answers for diverse question types. We have accomplished up to 92.16% F1 score considering partial match and 76.8% exact match on test dataset utilizing LSTM.