Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding
This work addresses the challenge of capturing colloquial medical expressions in diagnosis dialogue systems, representing an incremental improvement with domain-specific impact.
The paper tackles the problem of Medical Slot Filling (MSF) by formalizing it as a matching problem and proposing a Term Semantics Pre-trained Matching Network (TSPMN) with self-supervised objectives, resulting in improved performance on Chinese benchmarks, particularly in few-shot settings.
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.