Computational Argumentation-based Chatbots: A Survey
Journal of Artificial Intelligence Research · 02.08.2024 · 80 · 1271-1310
DOI: 10.1613/jair.1.15407 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 02.08.2024. Verfasst von Federico Castagna und 4 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref).
Abstract (Originalsprache)
Chatbots are conversational software applications designed to interact dialectically with users for a plethora of different purposes. Surprisingly, these colloquial agents have only recently been coupled with computational models of arguments (i.e. computational argumentation), whose aim is to formalise, in a machine-readable format, the ordinary exchange of information that characterises human communications. Chatbots may employ argumentation with different degrees and in a variety of manners. The present survey sifts through the literature to review papers concerning this kind of argumentation-based bot, drawing conclusions about the benefits and drawbacks that this approach entails in comparison with standard chatbots, while also envisaging possible future development and integration with the Transformer-based architecture and state-of-the-art Large Language models.
Zitieren
APA
Castagna, F., Kökciyan, N., Sassoon, I., Parsons, S., & Sklar, E. (2024). Computational Argumentation-based Chatbots: A Survey. Journal of Artificial Intelligence Research, 80, 1271-1310. https://doi.org/10.1613/jair.1.15407
Vancouver
Castagna F, Kökciyan N, Sassoon I, Parsons S, Sklar E. Computational Argumentation-based Chatbots: A Survey. Journal of Artificial Intelligence Research. 2024;80:1271-1310. doi:10.1613/jair.1.15407
BibTeX
@article{Castagna2024,
author = {Castagna, Federico and Kökciyan, Nadin and Sassoon, Isabel and Parsons, Simon and Sklar, Elizabeth},
title = {Computational Argumentation-based Chatbots: A Survey},
journal = {Journal of Artificial Intelligence Research},
year = {2024},
volume = {80},
pages = {1271--1310},
doi = {10.1613/jair.1.15407}
}
EUVIMED