Identification of Botany Terminology Based on Bert-BLSTM-CRF

Based on Baidu encyclopedia and CNKI botanical classification standards, we classify botanical terms into five categories in this paper: plant morphology and classification, plant ecology and geography, phytochemistry, plant heredity, plant technology and methods. In view of the difficulties in terms identification, we use a deep learning entity recognition model based on Bert-BLSTM-CRF to identify terms from large-scale corpus. In this paper, the Bert-BLSTM-CRF model is used to identify the professional terms in the field of botany, with an accuracy rate of 89.58%, a recall rate of 87.92% and an F1 value of 89.25%, indicating that the model could be effectively applied to the task of identifying the professional terms in botany. Based on the existing corpus, a comparative experiment is carried out in this paper, and the experimental results show that the model improves the recognition effect of professional terms in the field of botany.