Exploring the Influence of Dialog Input Format for Unsupervised Clinical Questionnaire Filling

Abstract

In the medical field, we have seen the emergence of health-bots that interact with patients to gather data and track their state. One of the downstream application is automatic questionnaire filling, where the content of the dialog is used to automatically fill a pre-defined medical questionnaire. Answering questions from the dialog context can be cast as a Natural Language Inference (NLI) task and therefore benefit from current pre-trained NLI models. However, these models have not been generally trained on dialog input format, which may have an influence on their performance. In this paper, we study the influence of dialog input format on the task. Our results demonstrate that dialog pre-processing and content selection can significantly improve performance of zero-shot models.

Tasks

Reproductions