Print Email Facebook Twitter The generalizability of argument quality dimensions in NLP models Title The generalizability of argument quality dimensions in NLP models Author Nguyen, Jakub (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Jonker, C.M. (mentor) Murukannaiah, P.K. (mentor) van der Meer, Michiel (mentor) Degree granting institution Delft University of Technology Programme Computer Science Date 2023-08-15 Abstract This research revolves around measuring the quality of arguments. High-quality arguments help in improving political discussions, resulting in better decision-making. Wachsmuth et al. developed a taxonomy breaking down argument quality into several dimensions. This work makes use of that taxonomy and combines it with modern NLP models. A cross-dataset examination of argument quality models was conducted. In particular, models were investigated on their generalizability between dimensions. Overall results show that there is no large difference in accuracy and agreement when models predict data of a quality dimension they were trained on, over dimensions they were not trained on. One can conclude that generalizations of argument quality dimensions with language models were not found. Nevertheless, qualitative analysis highlights findings that indicate some generalization to other dimensions. Subject Argument miningNatural language processingArtifical Intelligence To reference this document use: http://resolver.tudelft.nl/uuid:5e4f8ca8-a5fa-499d-877c-0d534de2e590 Part of collection Student theses Document type master thesis Rights © 2023 Jakub Nguyen Files PDF The_generalizability_of_a ... models.pdf 823.87 KB Close viewer /islandora/object/uuid:5e4f8ca8-a5fa-499d-877c-0d534de2e590/datastream/OBJ/view