Socially Aware Bias Measurements for Hindi Language Representations

10/15/2021
by   Vijit Malik, et al.
0

Language representations are an efficient tool used across NLP, but they are strife with encoded societal biases. These biases are studied extensively, but with a primary focus on English language representations and biases common in the context of Western society. In this work, we investigate the biases present in Hindi language representations such as caste and religion associated biases. We demonstrate how biases are unique to specific language representations based on the history and culture of the region they are widely spoken in, and also how the same societal bias (such as binary gender associated biases) when investigated across languages is encoded by different words and text spans. With this work, we emphasize on the necessity of social-awareness along with linguistic and grammatical artefacts when modeling language representations, in order to understand the biases encoded.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/10/2022

Speciesist Language and Nonhuman Animal Bias in English Masked Language Models

Various existing studies have analyzed what social biases are inherited ...
research
09/15/2021

Target Languages (vs. Inductive Biases) for Learning to Act and Plan

Recent breakthroughs in AI have shown the remarkable power of deep learn...
research
07/26/2023

How User Language Affects Conflict Fatality Estimates in ChatGPT

OpenAI's ChatGPT language model has gained popularity as a powerful tool...
research
11/25/2020

The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability

High-dimensional representations for words, text, images, knowledge grap...
research
05/17/2023

Shielded Representations: Protecting Sensitive Attributes Through Iterative Gradient-Based Projection

Natural language processing models tend to learn and encode social biase...
research
09/27/2021

Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework

Recent research has demonstrated how racial biases against users who wri...
research
05/14/2020

Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning

Human society had a long history of suffering from cognitive biases lead...

Please sign up or login with your details

Forgot password? Click here to reset