Automatically Extracting Information in Medical Dialogue: Expert System And Attention for Labelling

TL;DR

This paper introduces ESAL, a novel model combining expert systems and attention mechanisms with BERT to improve medical information extraction from dialogues, addressing previous limitations in recognizing categories.

Contribution

The paper presents a new model, ESAL, that effectively fuses expert systems and attention with BERT for enhanced medical dialogue information extraction.

Findings

ESAL significantly outperforms previous models in medical information classification.

The model effectively recognizes different categories in medical dialogues.

Experimental results demonstrate improved accuracy on a public dataset.

Abstract

Medical dialogue information extraction is becoming an increasingly significant problem in modern medical care. It is difficult to extract key information from electronic medical records (EMRs) due to their large numbers. Previously, researchers proposed attention-based models for retrieving features from EMRs, but their limitations were reflected in their inability to recognize different categories in medical dialogues. In this paper, we propose a novel model, Expert System and Attention for Labelling (ESAL). We use mixture of experts and pre-trained BERT to retrieve the semantics of different categories, enabling the model to fuse the differences between them. In our experiment, ESAL was applied to a public dataset and the experimental results indicated that ESAL significantly improved the performance of Medical Information Classification.