The dataset NTREX_bn_hi_benchmark provides news test references for Machine Translation (MT) evaluation, focusing on translations from Bengali to Hindi. As part of a larger collection supporting translations into 128 target languages, this dataset includes document-level information, making it an essential resource for multilingual MT benchmarking. Tailored for the news domain, it facilitates the evaluation of translation quality and aids in developing effective translation systems. Submitted by Microsoft, this dataset is a key resource for researchers and developers working on Bengali-to-Hindi translation tasks.
© 2026 - Copyright AIKosh. All rights reserved.