中文医学命名实体识别算法研究 |
点此下载全文 |
引用本文:李梦蝶,张平,李功利,等.中文医学命名实体识别算法研究[J].医学信息学杂志,2022,43(3):45-51 |
摘要点击次数: |
全文下载次数: |
|
基金项目:2020年中央引导地方科技发展专项科技扶贫类项目“屏山县多级联动互联网医院及智能特色专科平台研发与应用”(项目编号:2020ZYD002);四川省科技支撑项目“四川省肿瘤随访登记大数据服务平台建设”(项目编号:2019JDPT0008);四川省科技支撑项目“基于床垫式多参数监测系统的伤残病人智慧医疗监护系统”(项目编号:21ZDYF3601)。 |
|
中文摘要:针对中文医学命名实体识别任务中实体细粒度较大、识别准确率不高等问题,提出一种融合特征Albert的中文医学命名实体识别算法,利用自建的真实标注语料对模型进行训练与测试,结果表明模型具有较好的识别效果。 |
中文关键词:中文电子病历 命名实体识别算法 融合特征 Albert算法 |
|
Study on Chinese Medical Named Entity Recognition Algorithm |
|
|
Abstract:Aiming at the problems of large fine-grained entity and low recognition accuracy in Chinese medical Named Entity Recognition (NER) task, an algorithm of Chinese medical NER based on fusion features and Albert is proposed. The model is trained and tested by self-built real labeled corpus, and the results show that the model has good recognition effect. |
keywords:Chinese Electronic Medical Records (EMR) Named Entity Recognition (NER) algorithm fusion features Albert algorithm |
查看全文 查看/发表评论 下载PDF阅读器 |