AWdpCNER: Automated Wdp Chinese Named Entity Recognition from Wheat Diseases and Pests Text

Demeng Zhang, Guang Zheng, Hebing Liu, Xinming Ma and Lei Xi ()
Additional contact information
Demeng Zhang: College of Information and Management Sciences, Henan Agriculture University, Zhengzhou 450046, China
Guang Zheng: College of Information and Management Sciences, Henan Agriculture University, Zhengzhou 450046, China
Hebing Liu: College of Information and Management Sciences, Henan Agriculture University, Zhengzhou 450046, China
Xinming Ma: College of Information and Management Sciences, Henan Agriculture University, Zhengzhou 450046, China
Lei Xi: College of Information and Management Sciences, Henan Agriculture University, Zhengzhou 450046, China

Agriculture, 2023, vol. 13, issue 6, 1-14

Abstract: Chinese named entity recognition of wheat diseases and pests is an initial and key step in constructing knowledge graphs. In the field of wheat diseases and pests, there are problems, such as lack of training data, nested entities, fuzzy entity boundaries, diverse entity categories, and uneven entity distribution. To solve the above problems, two data augmentation methods were proposed to expand sentence semantic information on the premise of fully mining hidden knowledge. Then, a wheat diseases and pests dataset (WdpDs) for Chinese named entity recognition was constructed containing 21 types of entities and its domain dictionary (WdpDict), using a combination of manual and dictionary-based approaches, to better support the entity recognition task. Furthermore, an automated Wdp Chinese named entity recognition model (AWdpCNER) was proposed. This model was based on ALBERT-BiLSTM-CRF for entity recognition, and defined specific rules to calibrate entity boundaries after recognition. The model fusing ALBERT-BiLSTM-CRF and rules amendment achieved the best recognition results, with a precision of 94.76%, a recall of 95.64%, and an F1-score of 95.29%. Compared with the recognition results without rules amendment, the precision, recall, and F1-score was increased by 0.88 percentage points, 0.44 percentage points, and 0.75 percentage points, respectively. The experimental results showed that the proposed model could effectively identify Chinese named entities in the field of wheat diseases and pests, and this model achieved state-of-the-art recognition performance, outperforming several existing models, which provides a reference for other fields of named entities recognition such as food safety and biology.

Keywords: Chinese named entity recognition; wheat diseases and pests; data augmentation; ALBERT-BiLSTM-CRF; rules amendment (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/13/6/1220/pdf (application/pdf)
https://www.mdpi.com/2077-0472/13/6/1220/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:13:y:2023:i:6:p:1220-:d:1167548

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().