| 基于信息增强BERT的阴阳性判别 |
| 修订日期：2023-04-24 点此下载全文 |
| 引用本文：杨旋,薛敏,王翔,等.基于信息增强BERT的阴阳性判别[J].医学信息学杂志,2023,44(5):76-81 |
| 摘要点击次数: |
| 全文下载次数: |
|
|
| 中文摘要:介绍临床发现阴阳性判别任务要求,提出一种基于临床发现及其上下文信息增强BERT的阴阳性判别方法,阐述总体思路和建设路径,分析实验结果,该方法在2021年度中国健康信息处理大会(CHIP 2021)医学对话临床发现阴阳性判别任务的测试集上模型集成Macro-F1值达78.1%。 |
| 中文关键词:在线问诊 阴阳性判别 预训练语言模型 人工智能 自然语言处理 |
| |
| Classifying Positive and Negative Based on Information Enhanced BERT |
|
|
| Abstract:The paper introduces the task requirements of classifying positive and negative clinical findings, proposes a positive and negative discrimination method based on clinical findings and its context information enhanced BERT, expounds the general idea and construction path, and analyzes the experimental results. The results show that the method achieves a final Macro-F1 of 78.1% in the test set of the positive and negatived is crimination task of clinical findings in the 2021China Health Information Processing Conference(CHIP 2021). |
| keywords:online consultation classify positive and negative pre-trained language model artificial intelligence (AI) natural language processing(NLP) |
| 查看全文 查看/发表评论 下载PDF阅读器 |
