NTREX -- News Test References for MT Evaluation from English into a total of 128 target languages with document-level information.
NTREX-128/newstest2019-src.eng.txt - original source data
NTREX-128/newstest2019-ref.* - human translated references
LANGUAGES.tsv - mapping between ISO codes and language names
DOCUMENT_IDS.tsv - line aligned document boundaries
Data package has been released on 11/24/2022. Enjoy!
The NTREX-128 data set is released under the CC BY-SA 4.0 license.
@inproceedings{federmann-etal-2022-ntrex,
title = "{NTREX}-128 {--} News Test References for {MT} Evaluation of 128 Languages",
author = "Federmann, Christian and Kocmi, Tom and Xin, Ying",
booktitle = "Proceedings of the First Workshop on Scaling Up Multilingual Evaluation",
month = "nov",
year = "2022",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sumeval-1.4",
pages = "21--24",
}