SubmissionNumber#=%=#280
FinalPaperTitle#=%=#ShefCDTeam at SemEval-2024 Task 4: A Text-to-Text Model for Multi-Label Classification
ShortPaperTitle#=%=#
NumberOfPages#=%=#8
CopyrightSigned#=%=#Maggie Mi
JobTitle#==#
Organization#==#Department of Computer Science
The University of Sheffield 
Regent Court
211 Portobello
Sheffield
S1 4DP
UK
Abstract#==#This paper presents our findings for SemEval-2024 Task 4. We submit only to Subtask 1, applying the text-to-text framework to this task using a Flan-T5 model with a combination of parameter-efficient fine-tuning methods - Low-Rank Adaptation and Prompt Tuning. Overall, we find that the system performs well in English, but performance is limited in Bulgarian, North Macedonian and Arabic. Our analysis raises interesting questions about the effects of label order and label names when applying the text-to-text paradigm.
Author{1}{Firstname}#=%=#Meredith A.
Author{1}{Lastname}#=%=#Gibbons
Author{1}{Username}#=%=#magibbons
Author{1}{Email}#=%=#magibbons1@sheffield.ac.uk
Author{1}{Affiliation}#=%=#University of Sheffield
Author{2}{Firstname}#=%=#Maggie
Author{2}{Lastname}#=%=#Mi
Author{2}{Username}#=%=#mmi01
Author{2}{Email}#=%=#zmi1@sheffield.ac.uk
Author{2}{Affiliation}#=%=#University of Sheffield
Author{3}{Firstname}#=%=#Xingyi
Author{3}{Lastname}#=%=#Song
Author{3}{Username}#=%=#deansong
Author{3}{Email}#=%=#x.song@sheffield.ac.uk
Author{3}{Affiliation}#=%=#University of Sheffield
Author{4}{Firstname}#=%=#Aline
Author{4}{Lastname}#=%=#Villavicencio
Author{4}{Username}#=%=#avill
Author{4}{Email}#=%=#avill@essex.ac.uk
Author{4}{Affiliation}#=%=#Essex

==========
èéáğö