Skip to content

Opening book details…

Can I read BERT has a Moral Compass: Improvements of ethical and moral values of machines on EtoBox?

BERT has a Moral Compass: Improvements of ethical and moral values of machines by Schramowski, Patrick; Turan, Cigdem; Jentzsch, Sophie; Rothkopf, Constantin; Kersting, Kristian is a scholarly article available to read on EtoBox.

What is BERT has a Moral Compass: Improvements of ethical and moral values of machines about?

Allowing machines to choose whether to kill humans would be devastating for world peace and security. But how do we equip machines with the ability to learn ethical or even moral choices? Jentzsch et al.(2019) showed that applying machine learning to human texts can extract deontological ethical reasoning about "right" and "wrong" conduct by calculating a moral bias score on a sentence level using sentence embeddings. The machine learned that it is objectionable to kill living beings, but it is fine to kill time; It is essential to eat, yet one might not eat dirt; it is important to spread information, yet one should not spread misinformation. However, the evaluated moral bias was restricted to simple actions -- one verb -- and a ranking of actions with surrounding context. Recently BERT ---and variants such as RoBERTa and SBERT--- has set a new state-of-the-art performance for a wide range of NLP tasks. But has BERT also a better moral compass? In this paper, we discuss and show that this is indeed the case. Thus, recent improvements of language representations also improve the representation of the underlying ethical and moral values of the machine. We argue that through an advan

Author
Schramowski, Patrick; Turan, Cigdem; Jentzsch, Sophie; Rothkopf, Constantin; Kersting, Kristian
Published
2019
Language
EN

More by Schramowski, Patrick; Turan, Cigdem; Jentzsch, Sophie; Rothkopf, Constantin; Kersting, Kristian

Browse all works by Schramowski, Patrick; Turan, Cigdem; Jentzsch, Sophie; Rothkopf, Constantin; Kersting, Kristian