3 papers
cs.LG2024
Adaptive Tabu Dropout for Regularization of Deep Neural Network
Md. Tarek Hasan, Arifa Akter, Mohammad Nazmush Shamael +4
Dropout is an effective strategy for the regularization of deep neural networks. Applying tabu to the units that have been dropped in the recent epoch and retaining them for traini…
cs.CL2024
BanglishRev: A Large-Scale Bangla-English and Code-mixed Dataset of Product Reviews in E-Commerce
Mohammad Nazmush Shamael, Sabila Nawshin, Swakkhar Shatabda +1
This work presents the BanglishRev Dataset, the largest e-commerce product review dataset to date for reviews written in Bengali, English, a mixture of both and Banglish, Bengali w…
cs.LG2024
Deep Transfer Learning Based Peer Review Aggregation and Meta-review Generation for Scientific Articles
Md. Tarek Hasan, Mohammad Nazmush Shamael, H. M. Mutasim Billah +5
Peer review is the quality assessment of a manuscript by one or more peer experts. Papers are submitted by the authors to scientific venues, and these papers must be reviewed by pe…