Findings of the WMT 2021 shared task on quality estimation

Thumbnail
Name:
Findings_of_the_WMT_2021_Share ...
Embargo:
2022-09-27
Size:
1.289Mb
Format:
PDF
Download
Cast your vote
 
Your vote was cast
Thank you for your feedback
Authors
Specia, Lucia
Blain, Frederic
Fomicheva, Marina
Zerva, Chrysoula
Li, Zhenhao
Chaudhary, Vishrav
Martins, André
Issue Date
2021-12-31

Metadata
Show full item record
Abstract
We report the results of the WMT 2021 shared task on Quality Estimation, where the challenge is to predict the quality of the output of neural machine translation systems at the word and sentence levels. This edition focused on two main novel additions: (i) prediction for unseen languages, i.e. zero-shot settings, and (ii) prediction of sentences with catastrophic errors. In addition, new data was released for a number of languages, especially post-edited data. Participating teams from 19 institutions submitted altogether 1263 systems to different task variants and language pairs.
Citation
Specia, L., Blain, F., Fomicheva, M., Zerva, C., Li, Z., Chaudhary, V. and Martins, A.F.T. (in press) Findings of the WMT 2021 shared task on quality estimation. Proceedings of the Fifth Conference on Machine Translation, November 2021.
Publisher
Association for Computational Linguistics
URI
http://hdl.handle.net/2436/624392
Additional Links
http://statmt.org/wmt21/
Type
Conference contribution
Language
en
Description
© (in press) The Authors. Published by ACL. This is an open access article available under a Creative Commons licence. The published version can be accessed at the following link on the publisher’s website: [DOI/weblink]
Collections
https://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/