This study addresses the gap in translating Bangla regional dialects into standard Bangla by creating a large-scale multilingual benchmark dataset of 32,500 sentences in Bangla, Banglish, and English, representing five regional Bangla dialects such as Sylheti, Chittagong, Mymensingh, Noakhali, and Barishal.
benchmark dataset region-detection bleu-score mt5 word-error-rate mbert banglat5 bangla-bert-base bangla-regional-dialects dialect-translation standard-bangla
-
Updated
Oct 22, 2024 - Jupyter Notebook