Frustratingly Simple Prompting-based Text Denoising
Published in The Second Tiny Papers Track at ICLR 2024, 2024
This paper introduces a novel perspective on the automated essay scoring (AES) task, challenging the conventional view of the ASAP dataset as a static entity. Employing simple text denoising techniques using prompting, we explore the dynamic potential within the dataset. While acknowledging the previous emphasis on building regression systems, our paper underscores how making minor changes to a dataset through text denoising can enhance the final results.
Recommended citation: Park, J., & Qiu, M. (2024). Frustratingly simple prompting-based text denoising. The Second Tiny Papers Track at ICLR 2024. https://openreview.net/pdf?id=XlJRjhIkNi