AmazUtah_NLP at SemEval-2024 Task 9: A MultiChoice Question Answering System for Commonsense Defying Reasoning
This addresses the problem of improving NLP models' divergent thinking for researchers in computational linguistics, though it is incremental as it builds on existing pre-trained models and datasets.
The paper tackled the SemEval 2024 BRAINTEASER task, which tests language models' capacity for commonsense-defying reasoning through lateral thinking puzzles, achieving 92.5% accuracy on the Sentence Puzzle subtask and 80.2% on the Word Puzzle subtask.
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 subtasks 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 or 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.