Multi-Task Learning for Improving Gender Accuracy in Neural Machine Translation
Carlos Escolano, Graciela Ojeda, Christine Basta, Marta R. Costa-jussa
Abstract
Machine Translation is highly impacted by social biases present in data sets, indicating that it reflects and amplifies stereotypes. In this work, we study mitigating gender bias by jointly learning the translation, the part-of-speech, and the gender of the target language with different morphological complexity. This approach has shown improvements up to 6.8 points in gender accuracy without significantly impacting the translation quality.- Anthology ID:
- 2021.icon-main.3
- Volume:
- Proceedings of the 18th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2021
- Address:
- National Institute of Technology Silchar, Silchar, India
- Editors:
- Sivaji Bandyopadhyay, Sobha Lalitha Devi, Pushpak Bhattacharyya
- Venue:
- ICON
- SIG:
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 12–17
- Language:
- URL:
- https://aclanthology.org/2021.icon-main.3
- DOI:
- Cite (ACL):
- Carlos Escolano, Graciela Ojeda, Christine Basta, and Marta R. Costa-jussa. 2021. Multi-Task Learning for Improving Gender Accuracy in Neural Machine Translation. In Proceedings of the 18th International Conference on Natural Language Processing (ICON), pages 12–17, National Institute of Technology Silchar, Silchar, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Multi-Task Learning for Improving Gender Accuracy in Neural Machine Translation (Escolano et al., ICON 2021)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/2021.icon-main.3.pdf
- Data
- Universal Dependencies