CLAILGJun 12, 2021

Assessing Multilingual Fairness in Pre-trained Multimodal Representations

arXiv:2106.06683v2641 citations
Originality Incremental advance
AI Analysis

This addresses fairness issues in AI for multilingual users, highlighting biases that could affect equitable performance across different languages.

The study investigated whether pre-trained multilingual multimodal models treat languages equally, revealing severe multilingual accuracy disparities and biases across languages based on image attributes like race, gender, and age.

Recently pre-trained multimodal models, such as CLIP, have shown exceptional capabilities towards connecting images and natural language. The textual representations in English can be desirably transferred to multilingualism and support downstream multimodal tasks for different languages. Nevertheless, the principle of multilingual fairness is rarely scrutinized: do multilingual multimodal models treat languages equally? Are their performances biased towards particular languages? To answer these questions, we view language as the fairness recipient and introduce two new fairness notions, multilingual individual fairness and multilingual group fairness, for pre-trained multimodal models. Multilingual individual fairness requires that text snippets expressing similar semantics in different languages connect similarly to images, while multilingual group fairness requires equalized predictive performance across languages. We characterize the extent to which pre-trained multilingual vision-and-language representations are individually fair across languages. However, extensive experiments demonstrate that multilingual representations do not satisfy group fairness: (1) there is a severe multilingual accuracy disparity issue; (2) the errors exhibit biases across languages conditioning the group of people in the images, including race, gender and age.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes