BLEURT: Learning Robust Metrics for Text Generation
Article Status
Published
Authors/contributors
- Sellam, Thibault (Author)
- Das, Dipanjan (Author)
- Parikh, Ankur (Author)
Title
BLEURT: Learning Robust Metrics for Text Generation
Date
2020
Proceedings Title
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Conference Name
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Place
Online
Publisher
Association for Computational Linguistics
Pages
7881-7892
Language
en
Short Title
BLEURT
Accessed
16/10/2023, 19:38
Library Catalogue
DOI.org (Crossref)
Extra
<AI Smry>: BLEURT, a learned evaluation metric for English based on BERT, can model human judgment with a few thousand possibly biased training examples and yields superior results even when the training data is scarce and out-of-distribution.
Citation
Sellam, T., Das, D., & Parikh, A. (2020). BLEURT: Learning Robust Metrics for Text Generation. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 7881–7892. https://doi.org/10.18653/v1/2020.acl-main.704
Technical methods
Link to this record