Abstract
Different methods have been proposed to develop meta-embeddings from a given set of source embeddings. However, the source embeddings can contain unfair gender-related biases, and how these influence the meta-embeddings has not been studied yet.We study the gender bias in meta-embeddings created under three different settings:(1) meta-embedding multiple sources without performing any debiasing (Multi-Source No-Debiasing),(2) meta-embedding multiple sources debiased by a single method (Multi-Source Single-Debiasing), and(3) meta-embedding a single source debiased by different methods (Single-Source Multi-Debiasing).Our experimental results show that meta-embedding amplifies the gender biases compared to input source embeddings.We find that debiasing not only the sources but also their meta-embedding is needed to mitigate those biases.Moreover, we propose a novel debiasing method based on meta-embedding learning where we use multiple debiasing methods on a single source embedding and then create a single unbiased meta-embedding.- Anthology ID:
- 2022.findings-emnlp.227
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2022
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3118–3133
- Language:
- URL:
- https://aclanthology.org/2022.findings-emnlp.227
- DOI:
- Cite (ACL):
- Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. 2022. Gender Bias in Meta-Embeddings. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3118–3133, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Gender Bias in Meta-Embeddings (Kaneko et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2022.findings-emnlp.227.pdf