Debiasing Pre-trained Contextualised Embeddings

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, pages 1256–1266 April 19 - 23, 2021. ©2021 Association for Computational Linguistics 1256 Debiasing Pre-trained Contextualised Embeddings Masahiro Kaneko Tokyo Metropolitan University kaneko-masahiro@ed.tmu.ac.jp Danushka Bollegala∗ University of Liverpool, Amazon danushka@liverpool.ac.uk Abstract In comparison to the numerous debias- ing methods proposed for the static non- contextualised word embeddings, the discrim- inative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method that can be ap- plied at token- or sentence-levels to debias pre-trained contextualised embeddings. Our proposed method can be applied to any pre- trained contextualised embedding model, with- out requiring to retrain those models. Us- ing gender bias as an illustrative example, we then conduct a systematic study using sev- eral state-of-the-art (SoTA) contextualised rep- resentations on multiple benchmark datasets to evaluate the level of biases encoded in differ- ent contextualised embeddings before and af- ter debiasing using the proposed method. We find that applying token-level debiasing for all tokens and across all layers of a contextualised embedding model produces the best perfor- mance. Interestingly, we observe that there is a trade-off between creating an accurate vs. un- biased contextualised embedding model, and different contextualised embedding models re- spond differently to this trade-off. 1 Introduction Contextualised word embeddings have significantly improved performance in numerous natural lan- guage processing (NLP) applications (Devlin et al., 2019; Liu et al., 2019; Clark et al., 2020) and have established as the de facto standard for input text representations. Compared to static word em- beddings (Pennington et al., 2014; Mikolov et al., 2013) that represent a word by a single vector in all contexts it occurs, contextualised embeddings ∗Danushka Bollegala holds concurrent appointments as a Professor at University of Liverpool and as an Amazon Scholar. This paper describes work performed at the Univer- sity of Liverpool and is not associated with Amazon. use dynamic context dependent vectors for repre- senting a word in a specific context. Unfortunately however, it has been shown that, similar to their non-contextual counterparts, contextualised text embeddings also encode various types of unfair bi- ases (Zhao et al., 2019; Bordia and Bowman, 2019; May et al., 2019; Tan and Celis, 2019; Bommasani et al., 2020; Kurita et al., 2019). This is a worrying situation because such biases can easily propagate to the downstream NLP applications that use con- textualised text embeddings. Different types of unfair and discriminative bi- ases such as gender, racial and religious biases have been observed in static word embeddings (Boluk- basi et al., 2016; Zhao et al., 2018a; Rudinger et al., 2018; Zhao et al., 2018b; Elazar and Gold- berg, 2018; Kaneko and Bollegala, 2019). As dis- cussed later in § 2 different methods have been pro- posed for debiasing static word embeddings such as projection-based methods (Kaneko and Bollegala, 2019; Zhao et al., 2018b; Bolukbasi et al., 2016; Ravfogel et al., 2020) and adversarial methods (Xie et al., 2017; Gonen and Goldberg, 2019). In con- trast, despite …

Content truncated to 500 words