This paper explores methods for extracting information from radiology reports
that generalize across exam modalities to reduce requirements for annotated
data. We demonstrate that multi-pass T5-based text-to-text generative models
exhibit better generalization across exam modalities compared to approaches
that employ BERT-based task-specific classification layers. We then develop
methods that reduce the inference cost of the model, making large-scale corpus
processing more feasible for clinical applications. Specifically, we introduce
a generative technique that decomposes complex tasks into smaller subtask
blocks, which improves a single-pass model when combined with multitask
training. In addition, we leverage target-domain contexts during inference to
enhance domain adaptation, enabling use of smaller models. Analyses offer
insights into the benefits of different cost reduction strategies.

本文介绍了一种从放射学报告中提取信息以降低标注数据需求的方法，并比较了基于 BERT 的任务特定分类层和基于 T5 的多通道文本生成模型在应用领域中的泛化能力。另外，该文提出了创新的模型推理技术，将复杂任务分解为更小的子任务块，通过多任务联合训练实现了模型单次扫描时的高效率。同时，该文所述方法利用目标领域的上下文信息，增强了模型的领域自适应能力，进而使得在临床应用中更加便捷。