Clinical text classification with rule-based features and knowledge-guided convolutional neural networks.
Journal:
BMC medical informatics and decision making
Published Date:
Apr 4, 2019
Abstract
BACKGROUND: Clinical text classification is an fundamental problem in medical natural language processing. Existing studies have cocnventionally focused on rules or knowledge sources-based feature engineering, but only a limited number of studies have exploited effective representation learning capability of deep learning methods.