Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding
This work addresses the communication gap in medicine by improving text simplification for patients and healthcare professionals, though it is incremental.
The paper tackled the problem of low quality and diversity in medical text simplification by proposing an unlikelihood loss and reranked beam search decoding, achieving better performance on readability metrics across three datasets.
Text simplification has emerged as an increasingly useful application of AI for bridging the communication gap in specialized fields such as medicine, where the lexicon is often dominated by technical jargon and complex constructs. Despite notable progress, methods in medical simplification sometimes result in the generated text having lower quality and diversity. In this work, we explore ways to further improve the readability of text simplification in the medical domain. We propose (1) a new unlikelihood loss that encourages generation of simpler terms and (2) a reranked beam search decoding method that optimizes for simplicity, which achieve better performance on readability metrics on three datasets. This study's findings offer promising avenues for improving text simplification in the medical field.