ﻻ يوجد ملخص باللغة العربية
Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias against women at a comment level and present a model that can surface text likely to contain bias. Our main challenge is forcing the model to focus on signs of implicit bias, rather than other artifacts in the data. Thus, our methodology involves reducing the influence of confounds through propensity matching and adversarial learning. Our analysis shows how biased comments directed towards female politicians contain mixed criticisms, while comments directed towards other female public figures focus on appearance and sexualization. Ultimately, our work offers a way to capture subtle biases in various domains without relying on subjective human judgements.
Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly extended to
Gender diversity in the tech sector is - not yet? - sufficient to create a balanced ratio of men and women. For many women, access to computer science is hampered by socialization-related, social, cultural and structural obstacles. The so-called impl
In this paper, we quantify, analyze and mitigate gender bias exhibited in ELMos contextualized word vectors. First, we conduct several intrinsic analyses and find that (1) training data for ELMo contains significantly more male than female entities,
Various measures have been proposed to quantify human-like social biases in word embeddings. However, bias scores based on these measures can suffer from measurement error. One indication of measurement quality is reliability, concerning the extent t
With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted associations that fo