@文章{信息:doi/10.2196/38095，作者=“Phatak, Atharva and Savage, David W and Ohle, Robert and Smith, Jonathan and Mago, Vijay”，标题=“使用强化学习(TESLEA)的医学文本简化:基于深度学习的文本简化方法”，期刊=“JMIR Med Inform”，年=“2022”，月=“11”，日=“18”，卷=“10”，数=“11”，页=“e38095”，关键词=“医学文本简化;强化学习;自然语言处理;背景:在大多数情况下，医学领域的文章摘要是公开的。虽然每个人都能理解这些，但由于复杂的医学词汇，对更广泛的观众来说很难理解。因此，简化这些复杂的摘要是必不可少的，以使医学研究可为广大公众。目的:本研究旨在开发一种基于深度学习的文本简化(TS)方法，在保持生成文本质量的同时，将复杂的医学文本转换为更简单的版本。方法:采用强化学习和基于变压器的语言模型建立TS方法。相关性奖励、Flesch-Kincaid奖励和词汇简单性奖励进行了优化，以帮助将术语密集的复杂医学段落简化为更简单的版本，同时保留文本的质量。该模型使用3568个复杂-简单的医学段落进行训练，并通过自动化指标和人工注释对480个段落进行评估。 Results: The proposed method outperformed previous baselines on Flesch-Kincaid scores (11.84) and achieved comparable performance with other baselines when measured using ROUGE-1 (0.39), ROUGE-2 (0.11), and SARI scores (0.40). Manual evaluation showed that percentage agreement between human annotators was more than 70{\%} when factors such as fluency, coherence, and adequacy were considered. Conclusions: A unique medical TS approach is successfully developed that leverages reinforcement learning and accurately simplifies complex medical paragraphs, thereby increasing their readability. The proposed TS approach can be applied to automatically generate simplified text for complex medical text data, which would enhance the accessibility of biomedical research to a wider audience. ", issn="2291-9694", doi="10.2196/38095", url="https://medinform.www.mybigtv.com/2022/11/e38095", url="https://doi.org/10.2196/38095", url="http://www.ncbi.nlm.nih.gov/pubmed/36399375" }