Sadeque, Farig YousufRahman, Sheikh AyaturRonan, AtifSajid, Syed Saleh MohammadMahtab, MD Ajmain2025-01-052025-01-05©20242024-06ID 23141051ID 20201075ID 22241161ID 23141034http://hdl.handle.net/10361/25034Cataloged from PDF version of thesis.Includes bibliographical references (pages 51-52).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2024.Natural Language Inference (NLI) plays a vital role in our interpretation of textual data. Understanding texts is often difficult due to the logical and contextual motivations behind them. However, with the help of a text inference model, we can decode it. Our focus will be on Bengali Language Text inference, and we believe it will be useful in understanding the meaning of texts. In this thesis, we will introduce a high-quality Bangla Natural Language Inference dataset. We will also develop a benchmark model that will be able to effectively comprehend the complex semantic and logical relations among texts. The model will use complex deep-learning techniques to draw more meaningful conclusions from the texts. The research topic proposes many benefits, e.g., creating machines that will implement this model to create an effective question-answering system, an information retrieval system, sentiment analysis, and a decision maker.52 pagesenBrac 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.Natural language inferenceBangla NLIDeep learningMachine learningHypothesisEntailmentContradictionData mining.Machine learning.Natural language processing (Computer science).Thesis