Medical Slot Filling (MSF) task aims to convert medical queries into structured information, playing an essential role in diagnosis dialogue systems. However, the lack of sufficient term semantics learning makes existing approaches hard to capture semantically identical but colloquial expressions of terms in medical conversations. In this work, we formalize MSF into a matching problem and propose a Term Semantics Pre-trained Matching Network (TSPMN) that takes both terms and queries as input to model their semantic interaction. To learn term semantics better, we further design two self-supervised objectives, including Contrastive Term Discrimination (CTD) and Matching-based Mask Term Modeling (MMTM). CTD determines whether it is the masked term in the dialogue for each given term, while MMTM directly predicts the masked ones. Experimental results on two Chinese benchmarks show that TSPMN outperforms strong baselines, especially in few-shot settings.

翻译：医疗槽位填充（MSF，Medical Slot Filling）任务旨在将医疗查询转化为结构化信息，在诊断对话系统中扮演着至关重要的角色。然而，由于缺乏充分的术语语义学习，现有方法难以捕捉医疗对话中语义相同但表达口语化的术语。在本工作中，我们将医疗槽位填充形式化为一个匹配问题，并提出一种术语语义预训练匹配网络（TSPMN，Term Semantics Pre-trained Matching Network），该网络将术语和查询同时作为输入，以建模它们的语义交互。为了更好地学习术语语义，我们进一步设计了两个自监督目标，包括对比术语判别（CTD，Contrastive Term Discrimination）和基于匹配的掩码术语建模（MMTM，Matching-based Mask Term Modeling）。CTD判断每个给定术语是否为对话中被掩码的术语，而MMTM则直接预测被掩码的术语。在两个中文基准数据集上的实验结果表明，TSPMN优于强基线方法，尤其在少样本设置下表现突出。