Elfia Bezou-Vrakatseli of the 2021 cohort of the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence presented her paper, ‘Towards an Argument Scheme Classification for Ethical Reasoning’ at the Workshop on Computational Models of Natural Argument (CMNA 22) at the 9th International Conference on Computational Models of Argument (COMMA 2022).
In the paper, Elfia and her co-authors describe the progress towards realising the long-term research goal of supporting dialogue between humans and AI systems to enable transparent and rational joint reasoning, about matters of ethical significance. As Elfia explains, ‘In particular, the paper focuses on the current stage of my research, which consists of analysing natural language debates and identifying argument schemes and scheme taxonomies, specialised for ethical reasoning, that can support both the natural language processing needed to support human-AI dialogue, as well as for scaffolding human-human dialogue.”
For Elfia, the conference in Cardiff was an opportunity to network and was rewarding both personally and professionally. As Elfia said, “Attending the COMMA conference was a truly inspiring experience; finding myself among the brightest people in the field of argumentation, attending various thought-provoking talks, and getting to present my own work. More than that, meeting my fellow academics that share the same academic interests and passions resulted in countless captivating conversations that offered new perspectives.”
The paper is co-authored with Oana Cocarascu and Sanjay Modgil.