@inproceedings{mishra-ghashami-2024-amazutah,
    title = "{A}maz{U}tah{\_}{NLP} at {S}em{E}val-2024 Task 9: A {M}ulti{C}hoice Question Answering System for Commonsense Defying Reasoning",
    author = "Mishra, Soumya  and
      Ghashami, Mina",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2024.semeval-1.206/",
    doi = "10.18653/v1/2024.semeval-1.206",
    pages = "1436--1442",
    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."
}