重庆理工大学学报2024，Vol.38Issue(3)：189-197,9.DOI:10.3969/j.issn.1674-8425(z).2024.02.021
AMFRel:一种中文电子病历实体关系联合抽取方法
AMFRel:A method for joint extraction of entity relations in Chinese electronic medical records
摘要
Abstract
The entity relationship extraction of Chinese electronic medical records is a key part for constructing medical knowledge graphs and serving downstream tasks.Due to the complex relations in medical texts and high density of entities,inaccurate identification of medical terms and other problems may occur.To address these issues,a model called Adversarial Learning and Multi-Feature Fusion for Relation Triple Extraction-AMFRel is proposed in this paper.The model first extracts texts and part-of-speech features from medical text to obtain encoded vectors that incorporate part-of-speech information.Then,encoding vector is employed to generate adversarial samples by combining the perturbations generated by adversarial training to extract the subject of the sentence.Finally,the model enriches the structural features of the text by using an information fusion module,extracts the corresponding object based on specific relationship information,and obtains a triplet of medical text.Experiments are conducted on the CHIP2020 relation extraction dataset and the diabetes dataset.Our results show AMFRel achieves a precision of 63.922%,recall of 57.279%,and F1 score of 60.418%on the CHIP2020 relation extraction dataset,and a precision of 83.914%,recall of 67.021%,and F1 score of 74.522%on the diabetes dataset,demonstrating the triple extraction performance of this model is superior to other baseline models.关键词
关系抽取/联合抽取/对抗学习/多特征融合/关系重叠Key words
relation extraction/joint extraction/adversarial learning/multi feature fusion/relationship overlap分类
信息技术与安全科学引用本文复制引用
余肖生,李琳宇,周佳伦,马洪彬,陈鹏..AMFRel:一种中文电子病历实体关系联合抽取方法[J].重庆理工大学学报,2024,38(3):189-197,9.基金项目
国家重点研究发展计划项目(2016YFC0802500) （2016YFC0802500）
