Med7是一个可移植的临床自然语言处理模型，用于电子健康记录的命名实体识别任务，训练自MIMIC-III数据集，识别7类信息。模型包括tagger、parser和临床NER组件。通过预训练，模型在多种配置下表现良好，最高达到0.957的F1分数。安装推荐使用虚拟环境和spaCy 2.2.3。模型可用于识别药物、剂量、频率等实体，并能直观展示识别结果。
Med7
This repository dedicated to the first release of Med7: a transferable clinical natural language processing model for electronic health records, compatible with spaCy, for clinical named-entity recognition (NER) tasks. The en_core_med7_lg model is trained on MIMIC-III free-text electronic health records and is able to recognise 7 categories:
The trained model comprises three components in its pipeline:
tagger
parser
clinical NER with seven categories.
Self-supervised pre-training has shown its efficiency in achieving good results even with a small number of gold-annotated training data. We have experimented with the spacy pretrain approach and trained a number of weights for model initialisation for various parameters of the width a
最低0.47元/天 解锁文章
扫一扫
1930
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
