Principled Frameworks for Evaluating Ethics in NLP Systems
Computation and Language
2019-06-18 v1 Artificial Intelligence
Abstract
We critique recent work on ethics in natural language processing. Those discussions have focused on data collection, experimental design, and interventions in modeling. But we argue that we ought to first understand the frameworks of ethics that are being used to evaluate the fairness and justice of algorithmic systems. Here, we begin that discussion by outlining deontological ethics, and envision a research agenda prioritized by it.
Keywords
Cite
@article{arxiv.1906.06425,
title = {Principled Frameworks for Evaluating Ethics in NLP Systems},
author = {Shrimai Prabhumoye and Elijah Mayfield and Alan W Black},
journal= {arXiv preprint arXiv:1906.06425},
year = {2019}
}