SubmissionNumber#=%=#278
FinalPaperTitle#=%=#MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness
ShortPaperTitle#=%=#
NumberOfPages#=%=#12
CopyrightSigned#=%=#Robert Litschko
JobTitle#==#
Organization#==#
Abstract#==#This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness (STR), on Track C: Cross-lingual. The task aims to detect semantic relatedness of two sentences from the same languages. For cross-lingual approach we developed a set of linguistics-inspired models trained with several task-specific strategies. We 1) utilize language vectors for selection of donor languages; 2) investigate the multi-source approach for training; 3) use transliteration of non-latin script to study impact of "script gap"; 4) opt machine translation for data augmentation. We additionally compare the performance of XLM-RoBERTa and Furina with the same training strategy. Our submission achieved the first place in the C8 (Kinyarwanda) test.
Author{1}{Firstname}#=%=#Shijia
Author{1}{Lastname}#=%=#Zhou
Author{1}{Username}#=%=#gradiva
Author{1}{Email}#=%=#zhou.shijia@campus.lmu.de
Author{1}{Affiliation}#=%=#Ludwig Maximilian University of Munich
Author{2}{Firstname}#=%=#Huangyan
Author{2}{Lastname}#=%=#Shan
Author{2}{Username}#=%=#huangyanshan
Author{2}{Email}#=%=#shan.huangyan@campus.lmu.de
Author{2}{Affiliation}#=%=#LMU Munich
Author{3}{Firstname}#=%=#Barbara
Author{3}{Lastname}#=%=#Plank
Author{3}{Username}#=%=#bplank
Author{3}{Email}#=%=#bplank@gmail.com
Author{3}{Affiliation}#=%=#LMU Munich
Author{4}{Firstname}#=%=#Robert
Author{4}{Lastname}#=%=#Litschko
Author{4}{Username}#=%=#rml
Author{4}{Email}#=%=#rlitschk@cis.uni-muenchen.de
Author{4}{Affiliation}#=%=#LMU Munich

==========
èéáğö