SubmissionNumber#=%=#152
FinalPaperTitle#=%=#Groningen Group E at SemEval-2024 Task 8: Detecting machine-generated texts through pre-trained language models augmented with explicit linguistic-stylistic features
ShortPaperTitle#=%=#
NumberOfPages#=%=#9
CopyrightSigned#=%=#Marieke van der Holt
JobTitle#==#
Organization#==#
Abstract#==#Our approach to detecting machine-generated text for the SemEval-2024 Task 8 combines a wide range of linguistic-stylistic features with pre-trained language models (PLM). Experiments using random forests and PLMs resulted in an augmented DistilBERT system for subtask A and B and an augmented Longformer for subtask C. These systems achieved accuracies of 0.63 and 0.77 for the mono- and multilingual tracks of subtask A, 0.64 for subtask B and a MAE of 26.07 for subtask C. Although lower than the task organizer's baselines, we demonstrate that linguistic-stylistic features are predictors for whether a text was authored by a model (and if so, which one).
Author{1}{Firstname}#=%=#Patrick
Author{1}{Lastname}#=%=#Darwinkel
Author{1}{Email}#=%=#p.darwinkel@student.rug.nl
Author{1}{Affiliation}#=%=#University of Groningen
Author{2}{Firstname}#=%=#Sijbren
Author{2}{Lastname}#=%=#van Vaals
Author{2}{Email}#=%=#s.j.van.vaals@student.rug.nl
Author{2}{Affiliation}#=%=#University of Groningen
Author{3}{Firstname}#=%=#Marieke
Author{3}{Lastname}#=%=#van der Holt
Author{3}{Username}#=%=#mariekevdh
Author{3}{Email}#=%=#m.van.der.holt@student.rug.nl
Author{3}{Affiliation}#=%=#University of Groningen
Author{4}{Firstname}#=%=#Jarno
Author{4}{Lastname}#=%=#van Houten
Author{4}{Email}#=%=#j.t.van.houten@student.rug.nl
Author{4}{Affiliation}#=%=#University of Groningen

==========
èéáğö