
Research Article
A Lithium-Ion Battery Cathode Material Literature Entity Recognition Method Based on Deep Learning
@INPROCEEDINGS{10.1007/978-3-031-80713-8_8, author={Ziyu Yin and Gang Lei and Jianmao Xiao and Xinji Qiu and Qian Zhang and Lei Chang and Haohui Chen and Musheng Wu and Xushan Zhao}, title={A Lithium-Ion Battery Cathode Material Literature Entity Recognition Method Based on Deep Learning}, proceedings={Data Information in Online Environments. 4th EAI International Conference, DIONE 2023, Nanchang, China, November 25--27, 2023, Proceedings}, proceedings_a={DIONE}, year={2025}, month={2}, keywords={Lithium-ion Battery Materials Information Extraction Classification System Named Entity Identification}, doi={10.1007/978-3-031-80713-8_8} }
- Ziyu Yin
Gang Lei
Jianmao Xiao
Xinji Qiu
Qian Zhang
Lei Chang
Haohui Chen
Musheng Wu
Xushan Zhao
Year: 2025
A Lithium-Ion Battery Cathode Material Literature Entity Recognition Method Based on Deep Learning
DIONE
Springer
DOI: 10.1007/978-3-031-80713-8_8
Abstract
With the continuous deepening of research on lithium-ion battery materials, the number of literature in related fields has shown explosive growth, posing a challenge to researchers in terms of literature reading and information screening. Named entity recognition technology can automatically mark the pre-defined entity content in the literature, helping researchers to quickly locate the key information of the articles, and improve the reading rate of the literature. In this paper, the classification system of lithium-ion battery materials literature is constructed through the combination of automation and manual analysis, and the named entity recognition operation is conducted. We adopt the named entity recognition model based on BiLSTM-CRF, combined with Bert word embedding technology, to automatically identify and extract entities in the literature, and develope an automatic document annotation tool. Our work provides strong support for researchers to quickly understand the literature content and key information, and lays a foundation for subsequent relationship extraction and the construction of a Knowledge graph.