Standard
The Effect of Round-Trip Translation on Fairness in Sentiment Analysis. / Christiansen, Jonathan Gabel ; Gammelgaard, Mathias Lykke ; Søgaard, Anders.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. p. 4423–4428.
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Christiansen, JG, Gammelgaard, ML
& Søgaard, A 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. Association for Computational Linguistics, pp. 4423–4428, 2021 Conference on Empirical Methods in Natural Language Processing,
07/11/2021.
https://doi.org/10.18653/v1/2021.emnlp-main.363
APA
Christiansen, J. G., Gammelgaard, M. L.
, & Søgaard, A. (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 (pp. 4423–4428). Association for Computational Linguistics.
https://doi.org/10.18653/v1/2021.emnlp-main.363
Vancouver
Christiansen JG, Gammelgaard ML
, Søgaard A.
The Effect of Round-Trip Translation on Fairness in Sentiment Analysis. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. 2021. p. 4423–4428
https://doi.org/10.18653/v1/2021.emnlp-main.363
Author
Christiansen, Jonathan Gabel ; Gammelgaard, Mathias Lykke ; Søgaard, Anders. / The Effect of Round-Trip Translation on Fairness in Sentiment Analysis. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. pp. 4423–4428
Bibtex
@inproceedings{d972adf18c864d178fbfa411720181f5,
title = "The Effect of Round-Trip Translation on Fairness in Sentiment Analysis",
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.",
author = "Christiansen, {Jonathan Gabel} and Gammelgaard, {Mathias Lykke} and Anders S{\o}gaard",
year = "2021",
doi = "10.18653/v1/2021.emnlp-main.363",
language = "English",
pages = "4423–4428",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
publisher = "Association for Computational Linguistics",
note = "2021 Conference on Empirical Methods in Natural Language Processing ; Conference date: 07-11-2021 Through 11-11-2021",
}
RIS
TY - GEN
T1 - The Effect of Round-Trip Translation on Fairness in Sentiment Analysis
AU - Christiansen, Jonathan Gabel
AU - Gammelgaard, Mathias Lykke
AU - Søgaard, Anders
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
U2 - 10.18653/v1/2021.emnlp-main.363
DO - 10.18653/v1/2021.emnlp-main.363
M3 - Article in proceedings
SP - 4423
EP - 4428
BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
PB - Association for Computational Linguistics
T2 - 2021 Conference on Empirical Methods in Natural Language Processing
Y2 - 7 November 2021 through 11 November 2021
ER -