Constructing a Pluralist Moral Sentence Embedding Space using Contrastive Learning

Master Thesis (2023)
Author(s)

J. Park (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

C.M. Jonker – Mentor (TU Delft - Interactive Intelligence)

Pradeep Kumar Murukannaiah – Mentor (TU Delft - Interactive Intelligence)

E. Liscio – Mentor (TU Delft - Interactive Intelligence)

O.E. Scharenborg – Graduation committee member (TU Delft - Multimedia Computing)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2023 Jeongwoo Park
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Jeongwoo Park
Graduation Date
06-07-2023
Awarding Institution
Delft University of Technology
Programme
['Computer Science']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Moral values influence humans in decision-making. Pluralist moral philosophers argue that human morality can be represented by a finite number of moral values, respecting the differences in moral views. Recent advancements in NLP show that language models retain a discernible level of knowledge in deontological ethics and moral norms of society. However, a model which can only decide either right or wrong cannot fully understand the diverse moral perspectives of humans.

We propose a moral sentence embedding space, which can encompass moral differences, through the state-of-the-art Contrastive Learning framework. We evaluate the moral embedding space both intrinsically and extrinsically via three tasks: classification, moral similarity, and visual analysis. We show that our moral embedding space understands the characteristics of each moral value. Our results also highlight that moral rhetoric is seldom explicit in the text, emphasizing the necessity of additional information such as moral labels.

Files

Thesis_Jeongwoo_Park.pdf
(pdf | 6.76 Mb)
- Embargo expired in 01-01-2025
License info not available