BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text
Article Status
Published
Authors/contributors
- University of Wolverhampton, UK (Author)
- Saadany, Hadeel (Author)
- Orăsan, Constantin (Author)
- University of Surrey, UK (Author)
Title
BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text
Date
2021
Proceedings Title
Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021
Conference Name
TRanslation and Interpreting Technology ONline
Publisher
INCOMA Ltd. Shoumen, BULGARIA
Pages
48-56
ISBN
978-954-452-071-7
Short Title
BLEU, METEOR, BERTScore
Accessed
27/10/2023, 16:05
Library Catalogue
DOI.org (Crossref)
Extra
<AI Smry>: The ability of automatic quality metrics to detect critical machine translation errors which can cause serious misunderstanding of the affect message is assessed and the need for the fine-tuning of automatic metrics to make them more robust in detecting sentiment critical errors is demonstrated.
Citation
University of Wolverhampton, UK, Saadany, H., Orăsan, C., & University of Surrey, UK. (2021). BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Text. Proceedings of the Translation and Interpreting Technology Online Conference TRITON 2021, 48–56. https://doi.org/10.26615/978-954-452-071-7_006
Technical methods
Link to this record