Fairness in Natural Language Processing

Grant number: DP200102519 | Funding period: 2020 - 2023

Completed

Abstract

Natural language processing (NLP) has achieved spectacular commercial successes in recent years, and has been deployed across an ever-increasing breadth of devices and application areas. At the same time, there has been stark evidence to indicate that naively-trained models amplify biases in training data, and perform inconsistently across text relating to different demographic groupings of individuals. This project aims to systematically quantify the extent of such biases, and develop models that are both more socially equitable, as well as less prone to expose private data in the learned representations. In doing so, it will make NLP more accessible to new populations of users, and remove ..

View full description

Related publications (5)

EVERYBODY NEEDS GOOD NEIGHBOURS: AN UNSUPERVISED LOCALITY-BASED METHOD FOR BIAS MITIGATION

X Han, T Baldwin, T Cohn

2023-01-01

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP

X Han, T Baldwin, T Cohn

2023-01-01

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current p..

Does Representational Fairness Imply Empirical Fairness?

A Shen, X Han, T Cohn, T Baldwin, L Frermann

2022-01-01

NLP technologies can cause unintended harmsif learned representations encode sensitive attributes of the author, or predictions sy..

Towards Fair Supervised Dataset Distillation for Text Classification

X Han, A Shen, Y Li, L Frermann, T Baldwin, T Cohn

2022-01-01

With the growing prevalence of large-scale language models, their energy footprint and potential to learn and amplify historical b..

Give Me Convenience and Give Her Death: Who Should Decide What Uses of NLP are Appropriate, and on What Basis?

Kobi Leins, Jey Han Lau, Timothy Baldwin

2020-07-01

As part of growing NLP capabilities, coupled with an awareness of the ethical dimensions of research, questions have been raised a..

University of Melbourne Researchers

Trevor Cohn

Tim Baldwin

Lea Frermann