Measuring Social Biases in Grounded Vision and Language Embeddings

We generalize the notion of measuring social biases in word embeddings to visually grounded word embeddings. Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings. This is despite the fact that vision and language can suffer from...

全面介绍

书目详细资料
Main Authors: Ross, Candace, Barbu, Andrei, Katz, Boris
格式: 文件
出版: Center for Brains, Minds and Machines (CBMM), Annual Conference of the North American Chapter of the Association for Computational Linguistics (HLT/NAACL) 2022
在线阅读:https://hdl.handle.net/1721.1/141356