6 papers
BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning
Sajib Hossain, Md Kamrus Samad, Anan Ghosh +2
Deep neural networks have shown impressive success in NLP tasks owing to their complex structure and huge number of edges. Achieving state-of-the-art performance in natural languag…
Dynamic Temperature Scheduler for Knowledge Distillation
Sibgat Ul Islam, Jawad Ibn Ahad, Fuad Rahman +3
Knowledge Distillation (KD) trains a smaller student model using a large, pre-trained teacher model, with temperature as a key hyperparameter controlling the softness of output pro…
LegalRAG: A Hybrid RAG System for Multilingual Legal Information Retrieval
Muhammad Rafsan Kabir, Rafeed Mohammad Sultan, Fuad Rahman +4
Natural Language Processing (NLP) and computational linguistic techniques are increasingly being applied across various domains, yet their use in legal and regulatory tasks remains…
BanglaDialecto: An End-to-End AI-Powered Regional Speech Standardization
Md. Nazmus Sadat Samin, Jawad Ibn Ahad, Tanjila Ahmed Medha +4
This study focuses on recognizing Bangladeshi dialects and converting diverse Bengali accents into standardized formal Bengali speech. Dialects, often referred to as regional langu…
Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis
Jawad Ibn Ahad, Rafeed Mohammad Sultan, Abraham Kaikobad +4
This study investigates the automation of meta-analysis in scientific documents using large language models (LLMs). Meta-analysis is a robust statistical method that synthesizes th…
BanLemma: A Word Formation Dependent Rule and Dictionary Based Bangla Lemmatizer
Sadia Afrin, Md. Shahad Mahmud Chowdhury, Md. Ekramul Islam +10
Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning. H…