A survey of word embeddings for clinical text

被引：66

作者：

Khattak F.K. ^{[1
,3
,4
]}

Jeblee S. ^{[1
,3
]}

Pou-Prom C. ^{[1
,4
]}

Abdalla M. ^{[1
,3
]}

Meaney C. ^{[2
,3
]}

Rudzicz F. ^{[1
,3
,4
,5
]}

机构：

[1] Department of Computer Science, University of Toronto, Toronto, Ontario

[2] Department of Biostatistics, University of Toronto, Toronto, Ontario

[3] Vector Institute for Artificial Intelligence, Toronto, Ontario

[4] Li Ka Shing Knowledge Institute, St Michael's Hospital, Toronto, Ontario

[5] Surgical Safety Technologies Inc, Toronto, Ontario

来源：

Journal of Biomedical Informatics: X | 2019年 / 4卷

关键词：

Clinical data; Natural language processing; Word embeddings;

D O I：

10.1016/j.yjbinx.2019.100057

中图分类号：

学科分类号：

摘要：

Representing words as numerical vectors based on the contexts in which they appear has become the de facto method of analyzing text with machine learning. In this paper, we provide a guide for training these representations on clinical text data, using a survey of relevant research. Specifically, we discuss different types of word representations, clinical text corpora, available pre-trained clinical word vector embeddings, intrinsic and extrinsic evaluation, applications, and limitations of these approaches. This work can be used as a blueprint for clinicians and healthcare workers who may want to incorporate clinical text features in their own models and applications. © 2019 The Author(s)

引用