Enhance Chinese Medical Name Entity Recognition with Etymon Features

Abstract

Chinese medical name entity recognition aims to identify the boundaries and categories of medical entity from unstructured Chinese medical field texts. Traditional named entity recognition methods based on dictionaries and rules require a large amount of domain knowledge, hand-crafted rules or hand-crafted features. With the development of deep learning, end-to-end models are applied to named entity recognition and achieve high performance. In this paper, we propose a method for Chinese medical named entities recognition on the combination of Chinese radicals and etymon features in the classic character-based Bi-LSTM-CRF, which performs better than the state-of-art end-to-end deep learning models in our experiment.