The dataset NTREX_bn_kn_benchmark provides news test references for Machine Translation (MT) evaluation, focusing on translations from Bengali to Kannada. As part of a collection supporting translations into 128 target languages, this dataset includes document-level information, making it highly suitable for benchmarking multilingual translation models. Tailored for the news domain, it serves as a comprehensive resource for improving and assessing translation systems' quality and performance. Submitted by Microsoft, this dataset is invaluable for researchers and developers working on Bengali-to-Kannada translation tasks.
© 2026 - Copyright AIKosh. All rights reserved.