SemEval-2023 Task 4: ValueEval
Identification of Human Values Behind Arguments
- authored by
- Johannes Kiesel, Milad Alshomary, Nailia Mirzakhmedova, Maximilian Heinrich, Nicolas Handke, Henning Wachsmuth, Benno Stein
- Abstract
Argumentation is ubiquitous in natural language communication, from politics and media to everyday work and private life. Many arguments derive their persuasive power from human values, such as self-directed thought or tolerance, albeit often implicitly. These values are key to understanding the semantics of arguments, as they are generally accepted as justifications for why a particular option is ethically desirable. Can automated systems uncover the values on which an argument draws? To answer this question, 39 teams submitted runs to ValueEval’23. Using a multi-sourced dataset of over 9K arguments, the systems achieved F
1-scores up to 0.87 (nature) and over 0.70 for three more of 20 universal value categories. However, many challenges remain, as evidenced by the low peak F
1-score of 0.39 for stimulation, hedonism, face, and humility.
- Organisation(s)
-
Natural Language Processing Section
- External Organisation(s)
-
Bauhaus-Universität Weimar
Leipzig University
- Type
- Conference contribution
- Pages
- 2287-2303
- No. of pages
- 17
- Publication date
- 07.2023
- Publication status
- Published
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Theoretical Computer Science, Computer Science Applications, Computational Theory and Mathematics
- Electronic version(s)
-
https://doi.org/10.18653/V1/2023.SEMEVAL-1.313 (Access:
Open)
