AUTHOR=Zhang Ting , Wang Dengwu 

TITLE=Classification of crop disease-pest questions based on BERT-BiGRU-CapsNet with attention pooling

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1300580

DOI=10.3389/fpls.2023.1300580

ISSN=1664-462X

ABSTRACT=Crop disease-pest question classification is an essential part of pest knowledge intelligent question answering system. A crop disease-pest question classification method is proposed based on Bidirectional Encoder Representations from Transformers (BERT), Bidirectional gated unit (BiGRU), Capsule network (CapsNet) and attention pooling (BBGCAP). In BBGCAP, the unstructured text data is preprocessed vectorically using BERT, bidirectional gated unit (BiGRU) is used to extract the deep features of the text, attention pooling is used to assign the corresponding weights to the extracted deep information, and Capsule network (CapsNet) is used to route the right alternative. BBGCAP is a synthetic model by integrating the advantages of BERT, BiGRU, CapsNet and attention pooling. The experimental results on the cucumber pest question database show that the proposed method is superior to the methods based on traditional template matching, SVM and CNN-LSTM, and the accuracy of Precision, Recall and F1 are all above 902.15%. This method provides technical support for intelligent question answering system of crop disease-disease-pests.