Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories

By K. Chaloner, Alfredo Maldonado. 2019

56 citations recorded by the source corpus.

Prior work has shown that word embeddings capture human stereotypes, including gender bias. However, there is a lack of studies testing the presence of specific gender bias categories in word embeddings across diverse domains. This paper aims to fill this gap by applying the WEAT bias detection method to four sets of word embeddings trained on corpora from four different domains: news, social networking, biomedical and a gender-balanced corpus extracted from Wikipedia (GAP). We find that some domains are definitely more prone to gender bias than others, and that the categories of gender bias present also vary for each set of word embeddings. We detect some gender bias in GAP. We also propose a simple but novel method for discovering new bias categories by clustering word embeddings. We validate this method through WEAT’s hypothesis testing mechanism and find it useful for expanding the relatively small set of well-known gender bias word categories commonly used in the literature.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Safety, Robustness & Interpretability

Citations in the corpus

Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, background): “…et al. (2018); Thelwall (2018); Zhao et al. (2018b); Badjatiya et al. (2019); Bagdasaryan et al. (2019); Bamman et al. (2019); Cao and Daumé (2019); Chaloner and Maldonado (2019); Cho et al. (2019); Davidson et al. (2019); De-Arteaga et al. (2019); Fisher (2019); Font and Costa-jussà (2019);…”
Multi-Dimensional Gender Bias Classification (2020, background): “For example, statistical gender biases are rampant in word embeddings (Jurgens et al., 2012; Bolukbasi et al., 2016; Caliskan et al., 2017; Garg et al., 2018; Zhao et al., 2018b; Basta et al., 2019; Chaloner and Maldonado, 2019; Du et al., 2019; Gonen and Goldberg, 2019; Kaneko and Bollegala, 2019; ”
UNQOVERing Stereotypical Biases via Underspecified Questions (2020, neutral): “The majority of the work in the area is dedicated to pre-trained models, often via similaritybased analysis of the biases in input representations (Bolukbasi et al., 2016a; Garg et al., 2018; Chaloner and Maldonado, 2019; Bordia and Bowman, 2019; Tan and Celis, 2019; Zhao et al., 2019, 2020), or an ”
Neutralizing Gender Bias in Word Embedding with Latent Disentanglement and Counterfactual Generation (2020, methodology): “To quantify the gender bias, we use (Chaloner and Maldonado, 2019b) subset of masculine (A1) and feminine words(A2) as an attribute words, and use career (T1) and family (T2) related words for target words set.”
Unsupervised Discovery of Implicit Gender Bias (2020, background): “While corpus-level analyses, e.g. associations between gendered words and stereotypes, can be insightful (Bolukbasi et al., 2016; Fast et al., 2016; Caliskan et al., 2017; Garg et al., 2018; Friedman et al., 2019; Chaloner and Maldonado, 2019), they are difficult to interpret over short text spans.”
A Survey on Gender Bias in Natural Language Processing (2021, background): “For instance, Chaloner and Maldonado [2019] find evidence of bias in word embeddings trained on the GAP dataset when testing on a standard bias benchmark.”