Domain-specific Language Pre-training for Dialogue Comprehension on Clinical Inquiry-Answering Conversations

TL;DR

This paper introduces a domain-specific pre-training method for language models to enhance dialogue comprehension in clinical inquiry-answering conversations, addressing domain gaps and improving performance especially with limited data.

Contribution

It proposes a novel clinical domain-specific pre-training strategy with speaker and utterance manipulation, improving dialogue understanding in healthcare contexts.

Findings

Improved performance on clinical dialogue comprehension tasks.

Effective in low-resource training scenarios.

Bridged the gap between general language models and clinical domain.

Abstract

There is growing interest in the automated extraction of relevant information from clinical dialogues. However, it is difficult to collect and construct large annotated resources for clinical dialogue tasks. Recent developments in natural language processing suggest that large-scale pre-trained language backbones could be leveraged for such machine comprehension and information extraction tasks. Yet, due to the gap between pre-training and downstream clinical domains, it remains challenging to exploit the generic backbones for domain-specific applications. Therefore, in this work, we propose a domain-specific language pre-training, to improve performance on downstream tasks like dialogue comprehension. Aside from the common token-level masking pre-training method, according to the nature of human conversations and interactive flow of multi-topic inquiry-answering dialogues, we further propose sample generation strategies with speaker and utterance manipulation. The conversational pre-training guides the language backbone to reconstruct the utterances coherently based on the remaining context, thus bridging the gap between general and specific domains. Experiments are conducted on a clinical conversation dataset for symptom checking, where nurses inquire and discuss symptom information with patients. We empirically show that the neural model with our proposed approach brings improvement in the dialogue comprehension task, and can achieve favorable results in the low resource training scenario.