Shah et al. (2020): Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview
Abstract An increasing number of natural language processing papers address the effect of bias on predictions, introducing mitigation techniques at different parts of the standard NLP pipeline (data and models). However, these works have been conducted individually, without a unifying framework to organize efforts within the field. This situation leads to repetitive approaches, and focuses overly on bias symptoms/effects, rather than on their origins, which could limit the development of effective countermeasures. In this paper, we propose a unifying predictive bias framework for NLP. We summarize the NLP literature and suggest general mathematical definitions of predictive bias. We differentiate two consequences of bias: outcome disparities and error disparities, as well as four potential origins of biases: label bias, selection bias, model overamplification, and semantic bias. Our framework serves as an overview of predictive bias in NLP, integrating existing work into a single structure, and providing a conceptual baseline for improved frameworks.Click here to access the article.
Citation Shah, D.; Schwartz, H. A.; Hovy, D. (2020): Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics: 5248–5284.