More but Correct: Generating Diversified and Entity-revised Medical Response

TL;DR

This paper introduces a novel framework for Chinese medical dialogue generation that enhances response diversity and entity accuracy through a pipeline system and a new decoding mechanism, achieving competitive results in relevant competitions.

Contribution

We propose an entity prediction and fusion-based pipeline with Entity-revised Diverse Beam Search for improved medical dialogue response generation.

Findings

Wins CCKS and ICLR MLPCP Track 1 competitions

Improves entity correctness and response diversity

Demonstrates effectiveness in medical dialogue tasks

Abstract

Medical Dialogue Generation (MDG) is intended to build a medical dialogue system for intelligent consultation, which can communicate with patients in real-time, thereby improving the efficiency of clinical diagnosis with broad application prospects. This paper presents our proposed framework for the Chinese MDG organized by the 2021 China conference on knowledge graph and semantic computing (CCKS) competition, which requires generating context-consistent and medically meaningful responses conditioned on the dialogue history. In our framework, we propose a pipeline system composed of entity prediction and entity-aware dialogue generation, by adding predicted entities to the dialogue model with a fusion mechanism, thereby utilizing information from different sources. At the decoding stage, we propose a new decoding mechanism named Entity-revised Diverse Beam Search (EDBS) to improve entity correctness and promote the length and quality of the final response. The proposed method wins both the CCKS and the International Conference on Learning Representations (ICLR) 2021 Workshop Machine Learning for Preventing and Combating Pandemics (MLPCP) Track 1 Entity-aware MED competitions, which demonstrate the practicality and effectiveness of our method.