Measuring Bias in Contextualized Word Representations
arXiv:1906.07337
Abstract
Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case study focuses on gender bias, the proposed technique is generalizable to unveiling other biases, including in multiclass settings, such as racial and religious biases.
1st ACL Workshop on Gender Bias for Natural Language Processing 2019
References in corpus (7)
- Distributed Representations of Words and Phrases and their Compositionality
- Semantics derived automatically from language corpora contain human-like biases
- Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
- Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
- Learning Gender-Neutral Word Embeddings
- Evaluating the Underlying Gender Bias in Contextualized Word Embeddings
- Feature-Wise Bias Amplification
Cited by in corpus (4)
- Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective
- Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
- Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection
- Evaluating Metrics for Bias in Word Embeddings