期刊
出版社
IOS PRESS
DOI: 10.3233/SHTI230262
关键词
Language Models; ICF; Rehabilitation; Continual Training
In this paper, the authors tackle the challenging task of coding rehabilitation notes using ICF by developing a model based on the popular language model BERT. They effectively encode Italian rehabilitation notes by leveraging continual training of the model with ICF textual descriptions.
The coding of medical documents and in particular of rehabilitation notes using the International Classification of Functioning, Disability and Health (ICF) is a difficult task showing low agreement among experts. Such difficulty is mainly caused by the specific terminology that needs to be used for the task. In this paper, we address the task developing a model based on a large language model, BERT. By leveraging continual training of such a model using ICF textual descriptions, we are able to effectively encode rehabilitation notes expressed in Italian, an under-resourced language.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据