Principled Frameworks for Evaluating Ethics in NLP Systems
This work addresses the foundational problem of ethical evaluation in NLP systems, but it is incremental as it builds on existing critiques without presenting new empirical results.
The paper critiques existing approaches to ethics in NLP, arguing that a focus on data and modeling overlooks the need to understand underlying ethical frameworks, and it outlines deontological ethics to propose a new research agenda.
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.