Lexicon and attention-based named entity recognition for kiwifruit diseases and pests: A Deep learning approach

Lilin Zhang; Xiaolin Nie; Mingmei Zhang; Mingyang Gu; Violette Geissen; Coen J Ritsema; Dangdang Niu; Hongming Zhang

doi:10.3389/fpls.2022.1053449

Lexicon and attention-based named entity recognition for kiwifruit diseases and pests: A Deep learning approach

Front Plant Sci. 2022 Nov 17:13:1053449. doi: 10.3389/fpls.2022.1053449. eCollection 2022.

Authors

Lilin Zhang¹, Xiaolin Nie¹, Mingmei Zhang¹, Mingyang Gu¹, Violette Geissen², Coen J Ritsema², Dangdang Niu¹, Hongming Zhang¹

Affiliations

¹ College of Information Engineering, Northwest Agricultural and Forestry (A&F) University, Yangling, China.
² Soil Physics and Land Management Group, Wageningen University, Wageningen, Netherlands.

Abstract

Named Entity Recognition (NER) is a crucial step in mining information from massive agricultural texts, which is required in the construction of many knowledge-based agricultural support systems, such as agricultural technology question answering systems. The vital domain characteristics of Chinese agricultural text cause the Chinese NER (CNER) in kiwifruit diseases and pests to suffer from the insensitivity of common word segmentation tools to kiwifruit-related texts and the feature extraction capability of the sequence encoding layer being challenged. In order to alleviate the above problems, effectively mine information from kiwifruit-related texts to provide support for agricultural support systems such as agricultural question answering systems, this study constructed a novel Chinese agricultural NER (CANER) model KIWINER by statistics-based new word detection and two novel modules, AttSoftlexicon (Criss-cross attention-based Softlexicon) and PCAT (Parallel connection criss-cross attention), proposed in this paper. Specifically, new words were detected to improve the adaptability of word segmentation tools to kiwifruit-related texts, thereby constructing a kiwifruit lexicon. The AttSoftlexicon integrates word information into the model and makes full use of the word information with the help of Criss-cross attention network (CCNet). And the PCAT improves the feature extraction ability of sequence encoding layer through CCNet and parallel connection structure. The performance of KIWINER was evaluated on four datasets, namely KIWID (Self-annotated), Boson, ClueNER, and People's Daily, which achieved optimal F₁-scores of 88.94%, 85.13%, 80.52%, and 92.82%, respectively. Experimental results in many aspects illustrated that methods proposed in this paper can effectively improve the recognition effect of kiwifruit diseases and pests named entities, especially for diseases and pests with strong domain characteristics.

Keywords: Chinese named entity recognition; Criss-cross attention; data mining; deep learning; intelligent farming for diseases recognition; kiwifruit diseases and pests; lexicon; machine learning.