Ewoenam Kwaku Tokpo


pdf bib
How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification
Ewoenam Kwaku Tokpo | Pieter Delobelle | Bettina Berendt | Toon Calders
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

To mitigate gender bias in contextualized language models, different intrinsic mitigation strategies have been proposed, alongside many bias metrics. Considering that the end use of these language models is for downstream tasks like text classification, it is important to understand how these intrinsic bias mitigation strategies actually translate to fairness in downstream tasks and the extent of this. In this work, we design a probe to investigate the effects that some of the major intrinsic gender bias mitigation strategies have on downstream text classification tasks. We discover that instead of resolving gender bias, intrinsic mitigation techniques and metrics are able to hide it in such a way that significant gender information is retained in the embeddings. Furthermore, we show that each mitigation technique is able to hide the bias from some of the intrinsic bias measures but not all, and each intrinsic bias measure can be fooled by some mitigation techniques, but not all. We confirm experimentally, that none of the intrinsic mitigation techniques used without any other fairness intervention is able to consistently impact extrinsic bias. We recommend that intrinsic bias mitigation techniques should be combined with other fairness interventions for downstream tasks.


pdf bib
Text Style Transfer for Bias Mitigation using Masked Language Modeling
Ewoenam Kwaku Tokpo | Toon Calders
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop

It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Various research findings have concluded that biased texts have significant effects on target demographic groups. For instance, masculine-worded job advertisements tend to be less appealing to female applicants. In this paper, we present a text-style transfer model that can be trained on non-parallel data and be used to automatically mitigate bias in textual data. Our style transfer model improves on the limitations of many existing text style transfer techniques such as the loss of content information. Our model solves such issues by combining latent content encoding with explicit keyword replacement. We will show that this technique produces better content preservation whilst maintaining good style transfer accuracy.