SubmissionNumber#=%=#258
FinalPaperTitle#=%=#Team art-nat-HHU at SemEval-2024 Task 8: Stylistically Informed Fusion Model for MGT-Detection
ShortPaperTitle#=%=#
NumberOfPages#=%=#8
CopyrightSigned#=%=#Wiebke Petersen
JobTitle#==#
Organization#==#Heinrich-Heine-Universität Düsseldorf
Abstract#==#This paper presents our solution for subtask A of shared task 8 of SemEval 2024 for classifying human- and machine-written texts in English across multiple domains. We propose a fusion model consisting of RoBERTa based pre-classifier and two MLPs that have been trained to correct the pre-classifier using linguistic features. Our model achieved an accuracy of 85%.
Author{1}{Firstname}#=%=#Vittorio
Author{1}{Lastname}#=%=#Ciccarelli
Author{1}{Email}#=%=#Vittorio.Ciccarelli@hhu.de
Author{1}{Affiliation}#=%=#Heinrich Heine University
Author{2}{Firstname}#=%=#Cornelia
Author{2}{Lastname}#=%=#Genz
Author{2}{Email}#=%=#Cornelia.Genz@hhu.de
Author{2}{Affiliation}#=%=#Heinrich Heine University
Author{3}{Firstname}#=%=#Nele
Author{3}{Lastname}#=%=#Mastracchio
Author{3}{Email}#=%=#nele.mastracchio@hhu.de
Author{3}{Affiliation}#=%=#Heinrich Heine University
Author{4}{Firstname}#=%=#Wiebke
Author{4}{Lastname}#=%=#Petersen
Author{4}{Username}#=%=#wiebkepetersen
Author{4}{Email}#=%=#wiebke.petersen@hhu.de
Author{4}{Affiliation}#=%=#University of Düsseldorf
Author{5}{Firstname}#=%=#Anna Sophia
Author{5}{Lastname}#=%=#Stein
Author{5}{Username}#=%=#ansost
Author{5}{Email}#=%=#anna.stein@hhu.de
Author{5}{Affiliation}#=%=#Heinrich Heine Universität
Author{6}{Firstname}#=%=#Hanxin
Author{6}{Lastname}#=%=#Xia
Author{6}{Email}#=%=#Hanxin.Xia@hhu.de
Author{6}{Affiliation}#=%=#Heinrich Heine Uinversity

==========
èéáğö