The Effect of Round-Trip Translation on Fairness in Sentiment Analysis

Jonathan Gabel Christiansen, Mathias Gammelgaard, Anders Søgaard


Abstract
Sentiment analysis systems have been shown to exhibit sensitivity to protected attributes. Round-trip translation, on the other hand, has been shown to normalize text. We explore the impact of round-trip translation on the demographic parity of sentiment classifiers and show how round-trip translation consistently improves classification fairness at test time (reducing up to 47% of between-group gaps). We also explore the idea of retraining sentiment classifiers on round-trip-translated data.
Anthology ID:
2021.emnlp-main.363
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4423–4428
Language:
URL:
https://aclanthology.org/2021.emnlp-main.363
DOI:
10.18653/v1/2021.emnlp-main.363
Bibkey:
Cite (ACL):
Jonathan Gabel Christiansen, Mathias Gammelgaard, and Anders Søgaard. 2021. The Effect of Round-Trip Translation on Fairness in Sentiment Analysis. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4423–4428, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
The Effect of Round-Trip Translation on Fairness in Sentiment Analysis (Christiansen et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.363.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.363.mp4