Construction of a Question-Answer Dataset and Research on Named Entity Recognition in the Food Manufacturing Industry

DOI

10.2991/978-2-38476-277-4_33How to use a DOI?

Keywords

Named entity recognition; Food manufacturing industry; BERT-BiLSMT-CRF

Abstract

In recent years, food safety concerns have gained considerable attention, leading to an increasing demand in the food manufacturing industry for real-time monitoring, quality control, and traceability. Precise entity recognition becomes an effective means of extracting key information in addressing food-related issues. However, the lack of publicly available classify datasets in this domain emphasizes the urgent need to construct datasets tailored for the food manufacturing industry. In this study, we built a question-answering dataset for named entity recognition tasks and employed various models for training and evaluation. Experimental tests were conducted on four identification models based on BERT as the baseline model, using both publicly available datasets and the constructed dataset. The results indicate that the constructed dataset is suitable for named entity recognition tasks in the food manufacturing industry. Furthermore, the BERT-BiLSTM-CRF model outperforms other models in precision, recall, and F1 score, demonstrating its effectiveness in this domain.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yuqi Li
PY  - 2024
DA  - 2024/09/02
TI  - Construction of a Question-Answer Dataset and Research on Named Entity Recognition in the Food Manufacturing Industry
BT  - Proceedings of the 2024 10th International Conference on Humanities and Social Science Research (ICHSSR 2024)
PB  - Atlantis Press
SP  - 274
EP  - 281
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-277-4_33
DO  - 10.2991/978-2-38476-277-4_33
ID  - Li2024
ER  -