An Entity Recognition Model Based on Deep Learning Fusion of Text Feature

作者：

Highlights：

• A multi-feature entity recognition model is designed.

• A multi-feature word embedding algorithm is proposed, which integrates pinyin, radical and the meaning of the character itself, so that the word embedding vector has the characteristics of Chinese characters and the characteristics of diabetes text.

• In modeling, CNN and BiLSTM are used to extract the local and global features before and after the text sequence respectively, which solved the problem that the traditional method can not capture the dependence before and after the text sequence.

• CRF is used to output the predicted tag sequence.

摘要

•A multi-feature entity recognition model is designed.•A multi-feature word embedding algorithm is proposed, which integrates pinyin, radical and the meaning of the character itself, so that the word embedding vector has the characteristics of Chinese characters and the characteristics of diabetes text.•In modeling, CNN and BiLSTM are used to extract the local and global features before and after the text sequence respectively, which solved the problem that the traditional method can not capture the dependence before and after the text sequence.•CRF is used to output the predicted tag sequence.

论文关键词：Deep learning,Text features,Knowledge graph,Entity recognition,Relationship extraction

论文评审过程：Received 18 August 2021, Revised 25 November 2021, Accepted 1 December 2021, Available online 20 December 2021, Version of Record 20 December 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102841