Bengali to English Translation Benchmark Dataset
Bhashini's Bengali-English 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_en_benchmark provides news test references for Machine Translation (MT) evaluation, specifically for translations from Bengali to English. With coverage spanning 128 target languages, this dataset includes document-level information, making it highly suitable for benchmarking and enhancing multilingual MT models. Designed for the news domain, it offers a comprehensive testbed for evaluating translation quality and improving language models. Submitted by Microsoft, this dataset is a critical resource for researchers and developers working on Bengali-to-English MT 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 13:18:44
Open
Hosted
Activity Overview
0
21 
335 
1015.30 KB
Tags
- Translation
- Document-Level Evaluation
- NLP Dataset
- Language Modeling
- Bengali-English
- Bilingual Translation
- Benchmark
- News Domain
- Machine Translation
- Microsoft
License Control
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
data.json ( 1014.26 KB )
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(1015.30 KB)
- admin·1 year(s) ago
data.json
params.json
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.