This study presents three deidentified large medical text datasets, named
DISCHARGE, ECHO and RADIOLOGY, which contain 50K, 16K and 378K pairs of report
and summary that are derived from MIMIC-III, respectively. We implement
convincing baselines of automated abstractive summarization on the proposed
datasets with pre-trained encoder-decoder language models, including BERT2BERT,
T5-large and BART. Further, based on the BART model, we leverage the sampled
summaries from the train set as prior knowledge guidance, for encoding
additional contextual representations of the guidance with the encoder and
enhancing the decoding representations in the decoder. The experimental results
confirm the improvement of ROUGE scores and BERTScore made by the proposed
method, outperforming the larger model T5-large.

本研究提出了三个去识别化的医学文本数据集，命名为 DISCHARGE、ECHO 和 RADIOLOGY，共包含 50K、16K 和 378K 的报告和摘要对，作者在这些数据集上使用基于预训练编码器 - 解码器语言模型的有说服力的自动抽象摘要基线，并基于 BART 模型利用训练集的示例摘要作为先验知识引导来增强编码器和解码器的上下文表示，实验结果证实了这种方法在 ROUGE 分数和 BERTScore 上的改进，超过了更大模型 T5-large。