Case Study: Deontological Ethics in NLP

By Shrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov, Alan W. Black. 2020

34 citations recorded by the source corpus.

Recent work in natural language processing (NLP) has focused on ethical challenges such as understanding and mitigating bias in data and algorithms; identifying objectionable content like hate speech, stereotypes and offensive language; and building frameworks for better system design and data handling practices. However, there has been little discussion about the ethical foundations that underlie these efforts. In this work, we study one ethical theory, namely deontological ethics, from the perspective of NLP. In particular, we focus on the generalization principle and the respect for autonomy through informed consent. We provide four case studies to demonstrate how these principles can be used with NLP systems. We also recommend directions to avoid the ethical issues in these systems.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021, background): “We aim to support the ethical principles of autonomy and consent (Prabhumoye et al., 2021): knowing potential harmful impacts will allow researchers to make informed decisions about model release.”
On the Machine Learning of Ethical Judgments from Natural Language (2022, background): “Still other works like Prabhumoye et al. (2021) and Card and Smith (2020) focus on particular ethical theories and how they might be used in NLP to guide our modeling efforts, and Bender et al. (2020) foreground the importance of ethics training in NLP education.”
Five sources of bias in natural language processing (2021, background): “Prabhumoye et al. (2021) discuss this briefly in a case study for machine translation systems.”
The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems (2022, background): “There is a long-standing interest in the moral responsibility of AI (Dehghani et al., 2008; Alaieri and Vellino, 2016; Stephanidis et al., 2019; Zoshak and Dew, 2021; Prabhumoye et al., 2021; Schramowski et al., 2021).”