Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding
Lorenzo Jaime Flores, Heyuan Huang, Kejian Shi, Sophie Chheang, Arman Cohan
Abstract
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.- Anthology ID:
- 2023.findings-emnlp.322
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4859–4873
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.322
- DOI:
- 10.18653/v1/2023.findings-emnlp.322
- Cite (ACL):
- Lorenzo Jaime Flores, Heyuan Huang, Kejian Shi, Sophie Chheang, and Arman Cohan. 2023. Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4859–4873, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Medical Text Simplification: Optimizing for Readability with Unlikelihood Training and Reranked Beam Search Decoding (Flores et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.322.pdf