In recent years, the rapid advancement of machine learning (ML) models, particularly transformer-based pre-trained models, has revolutionized Natural Language Processing …
Machine learning models have been shown to inherit biases from their training datasets. This can be particularly problematic for vision-language foundation models trained on …
T Srinivasan, Y Bisk - arXiv preprint arXiv:2104.08666, 2021 - arxiv.org
Numerous works have analyzed biases in vision and pre-trained language models individually-however, less attention has been paid to how these biases interact in …
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking …
Intersectional bias is a bias caused by an overlap of multiple social factors like gender, sexuality, race, disability, religion, etc. A recent study has shown that word embedding …
Word embeddings are a widely used set of natural language processing techniques that map words to vectors of real numbers. These vectors are used to improve the quality of …
W Guo, A Caliskan - Proceedings of the 2021 AAAI/ACM Conference on …, 2021 - dl.acm.org
With the starting point that implicit human biases are reflected in the statistical regularities of language, it is possible to measure biases in English static word embeddings. State-of-the …
We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four …
Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating …