Author ORCID Identifier
Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence
Computer Sciences, Women's and gender studies
Natural language models and systems have been shown to reﬂect gender bias existing in training data. This bias can impact on the downstream task that machine learning models, built on this training data, are to accomplish. A variety of techniques have been proposed to mitigate gender bias in training data. In this paper we compare diﬀerent gender bias mitigation approaches on a classiﬁcation task. We consider mitigation techniques that manipulate the training data itself, including data scrubbing, gender swapping and counterfactual data augmentation approaches. We also look at using de-biased word embeddings in the representation of the training data. We evaluate the eﬀectiveness of the diﬀerent approaches at reducing the gender bias in the training data and consider the impact on task performance. Our results show that the performance of the classiﬁcation task is not aﬀected adversely by many of the bias mitigation techniques but we show a signiﬁcant variation in the eﬀectiveness of the diﬀerent gender bias mitigation techniques.
Sobhani, N., Delany, S.J. (2022). Exploring the Impact of Gender Bias Mitigation Approaches on a Downstream Classification Task. In: Ceci, M., Flesca, S., Masciari, E., Manco, G., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2022. Lecture Notes in Computer Science(), vol 13515. Springer, Cham. DOI: 10.1007/978-3-031-16564-1_10
Science Foundation Ireland
International Symposium on Methodologies for Intelligent Systems (ISMIS 2022)