Are We Consistently Biased? Multidimensional Analysis of Biases in Distributional Word Vectors

Abstract

Word embeddings have recently been shown to reflect many of the pronounced societal biases (e.g., gender bias or racial bias). Existing studies are, however, limited in scope and do not investigate the consistency of biases across relevant dimensions like embedding models, types of texts, and different languages. In this work, we present a systematic study of biases encoded in distributional word vector spaces: we analyze how consistent the bias effects are across languages, corpora, and embedding models. Furthermore, we analyze the cross-lingual biases encoded in bilingual embedding spaces, indicative of the effects of bias transfer encompassed in cross-lingual transfer of NLP models. Our study yields some unexpected findings, e.g., that biases can be emphasized or downplayed by different embedding models or that user-generated content may be less biased than encyclopedic text. We hope our work catalyzes bias research in NLP and informs the development of bias reduction techniques.

arXiv commentAccepted for *SEM 2019

References in corpus (6)

• Semantics derived automatically from language corpora contain human-like biases
• Exploiting Similarities among Languages for Machine Translation
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes
• Offline bilingual word vectors, orthogonal transformations and the inverted softmax
• Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings