MKA: A Scalable Medical Knowledge-Assisted Mechanism for Generative Models on Medical Conversation Tasks

Abstract

Using natural language processing (NLP) technologies to develop medical chatbots makes the diagnosis of the patient more convenient and efficient, which is a typical application in healthcare AI. Because of its importance, lots of researches have come out. Recently, the neural generative models have shown their impressive ability as the core of chatbot, while it cannot scale well when directly applied to medical conversation due to the lack of medical-specific knowledge. To address the limitation, a scalable medical knowledge-assisted mechanism (MKA) is proposed in this paper. The mechanism is aimed at assisting general neural generative models to achieve better performance on the medical conversation task. The medical-specific knowledge graph is designed within the mechanism, which contains 6 types of medical-related information, including department, drug, check, symptom, disease, and food. Besides, the specific token concatenation policy is defined to effectively inject medical information into the input data. Evaluation of our method is carried out on two typical medical datasets, MedDG and MedDialog-CN. The evaluation results demonstrate that models combined with our mechanism outperform original methods in multiple automatic evaluation metrics. Besides, MKA-BERT-GPT achieves state-of-the-art performance.

Knowledge grounded medical dialogue generation using augmented graphs

“…Liu et al 54 proposed an effective technique by auto encoding knowledge graphs for multimodal medical report generation using a knowledge-driven encoder and a knowledge-driven decoder. Similarly, Liang et al 55 presented a lightweight as well as a scalable mechanism using the transformer and BERT-GPT architecture to integrate the medical knowledge into different neural generative models on the MedDG and the MedDialog(CN) dialogue corpora. Lin et al 53 proposed a low-resource medical dialogue-generating system along with a Graph-Evolving Meta-Learning (GEML) framework that learns to evolve the commonsense graph for reasoning disease-symptom connections.…”

“…Liu et al 54 proposed an effective technique by auto encoding knowledge graphs for multimodal medical report generation using a knowledge-driven encoder and a knowledge-driven decoder. Similarly, Liang et al 55 presented a lightweight as well as a scalable mechanism using the transformer and BERT-GPT architecture to integrate the medical knowledge into different neural generative models on the MedDG and the…”

Retracted: MKA: A Scalable Medical Knowledge‐Assisted Mechanism for Generative Models on Medical Conversation Tasks

“…This article has been retracted by Hindawi following an investigation undertaken by the publisher [ 1 ]. This investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process: Discrepancies in scope Discrepancies in the description of the research reported Discrepancies between the availability of data and the research described Inappropriate citations Incoherent, meaningless and/or irrelevant content included in the article Peer-review manipulation …”

“…This article has been retracted by Hindawi following an investigation undertaken by the publisher [1]. This investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process:…”