Knowledge Graph Enhanced Transformers for Diagnosis Generation of Chinese Medicine
作者机构:School of Artificial Intelligence and Information TechnologyNanjing University of Chinese MedicineNanjing210023China School of Information ManagementNanjing UniversityNanjing210023China Jiangsu Collaborative Innovation Center of Traditional Chinese Medicine in Prevention and Treatment of TumorNanjing210023China Jiangsu Province Engineering Research Center of TCM Intelligence Health ServiceNanjing210023China
出 版 物:《Chinese Journal of Integrative Medicine》 (中国结合医学杂志(英文版))
年 卷 期:2024年第30卷第3期
页 面:267-276页
核心收录:
学科分类:1006[医学-中西医结合] 1002[医学-临床医学] 081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术(可授工学、理学学位)] 100602[医学-中西医结合临床] 10[医学]
基 金:Supported by the National Natural Science Foundation of China(No.82174276 and 82074580) the Key Research and Development Program of Jiangsu Province(No.BE2022712) China Postdoctoral Foundation(No.2021M701674) Postdoctoral Research Program of Jiangsu Province(No.2021K457C) Qinglan Project of Jiangsu Universities 2021
主 题:Chinese medicine diagnosis knowledge graph enhanced transformer text generation
摘 要:Chinese medicine(CM)diagnosis intellectualization is one of the hotspots in the research of CM *** traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues,however,it is difficult to solve the problems such as excessive or similar *** the development of natural language processing techniques,text generation technique has become increasingly *** this study,we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation *** semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory(BILSTM)with Transformer as the backbone ***,the CM diagnosis generation model Knowledge Graph Enhanced Transformer(KGET)was established by introducing the knowledge in medical field to enhance the inferential *** KGET model was established based on 566 CM case texts,and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence(LSTM-seq2seq),Bidirectional and Auto-Regression Transformer(BART),and Chinese Pre-trained Unbalanced Transformer(CPT),so as to analyze the model ***,the ablation experiments were performed to explore the influence of the optimized part on the KGET *** results of Bilingual Evaluation Understudy(BLEU),Recall-Oriented Understudy for Gisting Evaluation 1(ROUGE1),ROUGE2 and Edit distance of KGET model were 45.85,73.93,54.59 and 7.12,respectively in this *** with LSTM-seq2seq,BART and CPT models,the KGET model was higher in BLEU,ROUGE1 and ROUGE2 by 6.00–17.09,1.65–9.39 and 0.51–17.62,respectively,and lower in Edit distance by 0.47–*** ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model ***,the manual assessment indicated that the CM diagnosis results of the KGET model used