Bengali to Hindi Translation Benchmark Dataset
Bhashini's Bengali-Hindi Translation Benchmark is a detailed text dataset for testing machine translation quality. It includes document-level information and helps researchers build better multilingual translation systems.
About Dataset
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.
Dataset Metadata
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
NA
Sector Agnostic
Microsoft
Unstructured
NA
NA
N.A.
24/02/25 13:18:54
Open
Hosted
Activity Overview
0
15 
186 
1.39 MB
Tags
- Translation
- Document-Level Evaluation
- NLP Dataset
- Language Modeling
- Bilingual Translation
- Bengali-Hindi
- Benchmark
- News Domain
- Machine Translation
- Microsoft
License Control
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
data.json ( 1.39 MB )
To preview this file, you need to be a registered user. Please complete the registration process to gain access and continue viewing the content.
Data Quality Score Beta
Version Control
Version 1(1.39 MB)
- admin·11 month(s) ago
data.json
params.json
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.