Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information

Christine Basta, Marta R. Costa-jussà, José A. R. Fonollosa


Abstract
Gender bias negatively impacts many natural language processing applications, including machine translation (MT). The motivation behind this work is to study whether recent proposed MT techniques are significantly contributing to attenuate biases in document-level and gender-balanced data. For the study, we consider approaches of adding the previous sentence and the speaker information, implemented in a decoder-based neural MT system. We show improvements both in translation quality (+1 BLEU point) as well as in gender bias mitigation on WinoMT (+5% accuracy).
Anthology ID:
2020.winlp-1.25
Volume:
Proceedings of the Fourth Widening Natural Language Processing Workshop
Month:
July
Year:
2020
Address:
Seattle, USA
Editors:
Rossana Cunha, Samira Shaikh, Erika Varis, Ryan Georgi, Alicia Tsai, Antonios Anastasopoulos, Khyathi Raghavi Chandu
Venue:
WiNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
99–102
Language:
URL:
https://aclanthology.org/2020.winlp-1.25
DOI:
10.18653/v1/2020.winlp-1.25
Bibkey:
Cite (ACL):
Christine Basta, Marta R. Costa-jussà, and José A. R. Fonollosa. 2020. Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information. In Proceedings of the Fourth Widening Natural Language Processing Workshop, pages 99–102, Seattle, USA. Association for Computational Linguistics.
Cite (Informal):
Towards Mitigating Gender Bias in a decoder-based Neural Machine Translation model by Adding Contextual Information (Basta et al., WiNLP 2020)
Copy Citation:
Video:
 http://slideslive.com/38929564