SubmissionNumber#=%=#216
FinalPaperTitle#=%=#AmazUtah_NLP at SemEval-2024 Task 9: A MultiChoice Question Answering System for Commonsense Defying Reasoning
ShortPaperTitle#=%=#
NumberOfPages#=%=#7
CopyrightSigned#=%=#Soumya Smruti Mishra
JobTitle#==#
Organization#==#Amazon Web Services
Abstract#==#The SemEval 2024 BRAINTEASER task represents a pioneering venture in Natural Language Processing (NLP) by focusing on lateral thinking, a dimension of cognitive reasoning that is often overlooked in traditional linguistic analyses. This challenge comprises of Sentence Puzzle and Word Puzzle sub-tasks and aims to test language models' capacity for divergent thinking. 

In this paper, we present our approach to the BRAINTEASER task. We employ a holistic strategy by leveraging cutting-edge pre-trained models in multiple choice architecture, and diversify the training data with Sentence and Word Puzzle datasets. To gain further improvement, we fine-tuned the model with synthetic humor/jokes dataset and the RiddleSense dataset which helped augmenting the model's lateral thinking abilities. Empirical results show that our approach achieve 92.5% accuracy in Sentence Puzzle subtask and 80.2% accuracy in Word Puzzle subtask.
Author{1}{Firstname}#=%=#Soumya Smruti
Author{1}{Lastname}#=%=#Mishra
Author{1}{Username}#=%=#soumyasmruti
Author{1}{Email}#=%=#soumyasmruti@gmail.com
Author{1}{Affiliation}#=%=#Amazon Web Services
Author{2}{Firstname}#=%=#Mina
Author{2}{Lastname}#=%=#Ghashami
Author{2}{Email}#=%=#mina.ghashami@gmail.com
Author{2}{Affiliation}#=%=#Amazon Web Services

==========
èéáğö