SubmissionNumber#=%=#217
FinalPaperTitle#=%=#IITK at SemEval-2024 Task 1: Contrastive Learning and Autoencoders for Semantic Textual Relatedness in Multilingual Texts
ShortPaperTitle#=%=#
NumberOfPages#=%=#6
CopyrightSigned#=%=#Ashutosh Modi
JobTitle#==#
Organization#==#IIT Kanpur, Kanpur, 208016, U.P., India
Abstract#==#This paper describes our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness. The challenge is focused on automatically detecting the degree of relatedness between pairs of sentences for 14 languages including both high and low-resource Asian and African languages. Our team participated in two subtasks consisting of Track A: supervised and Track B: unsupervised. This paper focuses on a BERT-based contrastive learning and similarity metric based approach primarily for the supervised track while exploring autoencoders for the unsupervised track. It also aims on the creation of a bigram relatedness corpus using negative sampling strategy, thereby producing refined word embeddings.
Author{1}{Firstname}#=%=#Udvas
Author{1}{Lastname}#=%=#Basak
Author{1}{Username}#=%=#udvasbasak
Author{1}{Email}#=%=#udv.ion8679@gmail.com
Author{1}{Affiliation}#=%=#Indian Institute of Technology Kanpur
Author{2}{Firstname}#=%=#Rajarshi
Author{2}{Lastname}#=%=#Dutta
Author{2}{Username}#=%=#rajarshid
Author{2}{Email}#=%=#rajarshidutta2015@gmail.com
Author{2}{Affiliation}#=%=#Indian Institute of Technology Kanpur
Author{3}{Firstname}#=%=#Shivam
Author{3}{Lastname}#=%=#Pandey
Author{3}{Username}#=%=#shivampandey
Author{3}{Email}#=%=#shivam8711@gmail.com
Author{3}{Affiliation}#=%=#Indian Institute of Technology Kanpur
Author{4}{Firstname}#=%=#Ashutosh
Author{4}{Lastname}#=%=#Modi
Author{4}{Username}#=%=#ashutosh
Author{4}{Email}#=%=#ashutoshm@cse.iitk.ac.in
Author{4}{Affiliation}#=%=#Indian Institute of Technology Kanpur

==========
èéáğö