Med-EASi：用于医学文本可控简化的精细注释数据集和模型
Med-EASi: Finely Annotated Dataset and Models for Controllable Simplification of Medical Texts
摘要：
自动医疗文本简化可以帮助提供者进行患者友好的沟通，使医疗文本更容易获得，从而提高健康素养。但是，为这项任务策划一个高质量的语料库需要医学专家的监督。在这项工作中，我们提出了$\textbf{Med-EASi}$（$\underline{\textbf{Med}}$ ical dataset for $\underline{\textbf{E}}$ labative and $\underline{\textbf{A}}$ bstractive $\underline{\textbf{Si}}$ mplification），一个独特的众包和精细注释的数据集，用于监督简化简短的医学文本。它的$\textit{expert-layman-AI collaborative}$注释通过标记四种文本转换（细化、替换、删除和插入），促进了$\textit{controllability}$对文本的简化。为了学习医学文本简化，我们使用四种不同风格的输入输出组合对T5-large进行了微调，从而产生了两个无控制和两个可控版本的模型。通过使用多角度训练方法，我们将两种类型的$\textit{controllability}$添加到文本简化中：$\textit{position-aware}$，它使用就地注释的输入和输出，以及$\textit{position-agnostic}$，其中模型只知道要编辑的内容，但不知道它们的位置。我们的研究结果表明，我们的细粒度的注释提高学习相比，未注释的基线。此外，$\textit{position-aware}$控制比$\textit{position-agnostic}$控制产生更好的简化。数据和代码可在https://github.com/Chandrayee/CTRL-SIMP上获得。
英文摘要：
Automatic medical text simplification can assist providers with patient-friendly communication and make medical texts more accessible, thereby improving health literacy. But curating a quality corpus for this task requires the supervision of medical experts. In this work, we present $\textbf{Med-EASi}$ ($\underline{\textbf{Med}}$ical dataset for $\underline{\textbf{E}}$laborative and $\underline{\textbf{A}}$bstractive $\underline{\textbf{Si}}$mplification), a uniquely crowdsourced and finely annotated dataset for supervised simplification of short medical texts. Its $\textit{expert-layman-AI collaborative}$ annotations facilitate $\textit{controllability}$ over text simplification by marking four kinds of textual transformations: elaboration, replacement, deletion, and insertion. To learn medical text simplification, we fine-tune T5-large with four different styles of input-output combinations, leading to two control-free and two controllable versions of the model. We add two types of $\textit{controllability}$ into text simplification, by using a multi-angle training approach: $\textit{position-aware}$, which uses in-place annotated inputs and outputs, and $\textit{position-agnostic}$, where the model only knows the contents to be edited, but not their positions. Our results show that our fine-grained annotations improve learning compared to the unannotated baseline. Furthermore, $\textit{position-aware}$ control generates better simplification than the $\textit{position-agnostic}$ one. The data and code are available at https://github.com/Chandrayee/CTRL-SIMP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
