Towards devising an efficient VQA in the Bengali Language

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2021.

Bibliographic Details
Main Authors:	Islam, S M Shahriar, Auntor, Riyad Ahsan, Islam, Minhajul, Chowdhury, Tahmin Haider, Hossain Anik, Mohammad Yousuf
Other Authors:	Noor, Jannatun
Format:	Thesis
Language:	en_US
Published:	Brac University 2022
Subjects:	Natural Language Processing CLEVR VQA V1 Visual Question Answering Natural language processing (Computer science).
Online Access:	http://hdl.handle.net/10361/17594

id	10361-17594
record_format	dspace
spelling	10361-175942022-11-21T21:01:42Z Towards devising an efficient VQA in the Bengali Language Islam, S M Shahriar Auntor, Riyad Ahsan Islam, Minhajul Chowdhury, Tahmin Haider Hossain Anik, Mohammad Yousuf Noor, Jannatun Department of Computer Science and Engineering, Brac University Natural Language Processing CLEVR VQA V1 Visual Question Answering Natural language processing (Computer science). This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2021. Cataloged from PDF version of thesis. Includes bibliographical references (pages 50-53). This paper aims to provide insight into how Visual question answering might work on Bangla datasets versus English datasets. Several studies have been conducted on deep learning methods applied to Bangla datasets up to this point. However, a Bangla dataset with images and questions embedded in each of them has yet to be created. We attempted to create a Bangla dataset suitable for such implementation through our re search. The step-by-step procedures in our work demonstrate how various bar riers can be overcome while developing datasets. We attempted to use existing visual question answering datasets because there are no actual Bangla datasets created for this specific task.In the end we successfully created our own Bangla visual question an swering datasets and proposed a model to train and compare among existing datasets. Following that, the comparison was provided to show how the Bangla dataset differs from the English datasets in terms of the VQA model. Our work should make more than enough room for future research and implementation of visual question answering tasks in Bangla. S M Shahriar Islam Riyad Ahsan Auntor Minhajul Islam Tahmin Haider Chowdhury Mohammad Yousuf Hossain Anik B. Computer Science 2022-11-21T04:53:02Z 2022-11-21T04:53:02Z 2021 2021-12 Thesis ID: 18101456 ID: 18101358 ID: 18101304 ID: 18101056 ID: 18101586 http://hdl.handle.net/10361/17594 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 53 Pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	en_US
topic	Natural Language Processing CLEVR VQA V1 Visual Question Answering Natural language processing (Computer science).
spellingShingle	Natural Language Processing CLEVR VQA V1 Visual Question Answering Natural language processing (Computer science). Islam, S M Shahriar Auntor, Riyad Ahsan Islam, Minhajul Chowdhury, Tahmin Haider Hossain Anik, Mohammad Yousuf Towards devising an efficient VQA in the Bengali Language
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2021.
author2	Noor, Jannatun
author_facet	Noor, Jannatun Islam, S M Shahriar Auntor, Riyad Ahsan Islam, Minhajul Chowdhury, Tahmin Haider Hossain Anik, Mohammad Yousuf
format	Thesis
author	Islam, S M Shahriar Auntor, Riyad Ahsan Islam, Minhajul Chowdhury, Tahmin Haider Hossain Anik, Mohammad Yousuf
author_sort	Islam, S M Shahriar
title	Towards devising an efficient VQA in the Bengali Language
title_short	Towards devising an efficient VQA in the Bengali Language
title_full	Towards devising an efficient VQA in the Bengali Language
title_fullStr	Towards devising an efficient VQA in the Bengali Language
title_full_unstemmed	Towards devising an efficient VQA in the Bengali Language
title_sort	towards devising an efficient vqa in the bengali language
publisher	Brac University
publishDate	2022
url	http://hdl.handle.net/10361/17594
work_keys_str_mv	AT islamsmshahriar towardsdevisinganefficientvqainthebengalilanguage AT auntorriyadahsan towardsdevisinganefficientvqainthebengalilanguage AT islamminhajul towardsdevisinganefficientvqainthebengalilanguage AT chowdhurytahminhaider towardsdevisinganefficientvqainthebengalilanguage AT hossainanikmohammadyousuf towardsdevisinganefficientvqainthebengalilanguage
_version_	1814309295482732544

Towards devising an efficient VQA in the Bengali Language

Similar Items