Chinese Named Entity Recognition in Business Domain Based on Bi-LSTM-CRF
Download as PDF
DOI: 10.23977/ESAC2020006
Author(s)
Yanbo Li, Yifei Xin, Yunlin Fu
Corresponding Author
Yanbo Li
ABSTRACT
In order to solve the problem of disorder, disorder and fragmentation of multi-source and heterogeneous enterprise data on the current network open platform, a Bi-LSTM-CRF deep learning model is proposed to identify named entities in the commercial field. The method includes three types of named entities: enterprise full name entity, enterprise abbreviation entity and person entity. The experimental results show that the average F value of the recognition rate of enterprise full name entity, enterprise abbreviation entity and person entity is 90.85%, which verifies the effectiveness of the proposed method. It is proved that this study effectively improves the efficiency of named entity recognition in the business field.
KEYWORDS
Business Domain; Named Entity Recognition; Deep Learning; Bi-LSTM-CRF