SubmissionNumber#=%=#207
FinalPaperTitle#=%=#UIC NLP GRADS at SemEval-2024 Task 3: Two-Step Disjoint Modeling for Emotion-Cause Pair Extraction
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#Sharad Chandakacherla
JobTitle#==#
Organization#==#Department of Computer Science, University of Illinois at Chicago, Chicago, Illinois, USA - 60607
Abstract#==#Disentangling underlying factors contributing to the expression of emotion in multimodal data is challenging but may accelerate progress toward many real-world applications. In this paper we describe our approach for solving SemEval-2024 Task #3, Sub-Task #1, focused on identifying utterance-level emotions and their causes using the text available from the multimodal F.R.I.E.N.D.S. television series dataset. We propose to disjointly model emotion detection and causal span detection, borrowing a paradigm popular in question answering (QA) to train our model. Through our experiments we find that (a) contextual utterances before and after the target utterance play a crucial role in emotion classification; and (b) once the emotion is established, detecting the causal spans resulting in that emotion using our QA-based technique yields promising results.
Author{1}{Firstname}#=%=#Sharad
Author{1}{Lastname}#=%=#Chandakacherla
Author{1}{Username}#=%=#sharadc
Author{1}{Email}#=%=#schand65@uic.edu
Author{1}{Affiliation}#=%=#University of Illinois at Chicago
Author{2}{Firstname}#=%=#Vaibhav
Author{2}{Lastname}#=%=#Bhargava
Author{2}{Username}#=%=#vbharg
Author{2}{Email}#=%=#vbharg4@uic.edu
Author{2}{Affiliation}#=%=#University of Illinois at Chicago
Author{3}{Firstname}#=%=#Natalie
Author{3}{Lastname}#=%=#Parde
Author{3}{Username}#=%=#natalieparde
Author{3}{Email}#=%=#parde@uic.edu
Author{3}{Affiliation}#=%=#University of Illinois at Chicago

==========
èéáğö