Named entity recognition for Chinese based on global pointer and adversarial training
Abstract Named entity recognition aims to identify entities from unstructured text and is an important subtask for natural language processing and building knowledge graphs. Most of the existing entity recognition methods use conditional random fields as label decoders or use pointer networks for en...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-30355-y |
| _version_ | 1797864832878247936 |
|---|---|
| author | Hongjun Li Mingzhe Cheng Zelin Yang Liqun Yang Yansong Chua |
| author_facet | Hongjun Li Mingzhe Cheng Zelin Yang Liqun Yang Yansong Chua |
| author_sort | Hongjun Li |
| collection | DOAJ |
| description | Abstract Named entity recognition aims to identify entities from unstructured text and is an important subtask for natural language processing and building knowledge graphs. Most of the existing entity recognition methods use conditional random fields as label decoders or use pointer networks for entity recognition. However, when the number of tags is large, the computational cost of method based on conditional random fields is high and the problem of nested entities cannot be solved. The pointer network uses two modules to identify the first and the last of the entities separately, and a single module can only focus on the information of the first or the last of the entities, but cannot pay attention to the global information of the entities. In addition, the neural network model has the problem of local instability. To solve mentioned problems, a named entity recognition model based on global pointer and adversarial training is proposed. To obtain global entity information, global pointer is used to decode entity information, and rotary relative position information is considered in the model designing to improve the model’s perception of position; to solve the model’s local instability problem, adversarial training is used to improve the robustness and generalization of the model. The experimental results show that the F1 score of the model are improved on several public datasets of OntoNotes5, MSRA, Resume, and Weibo compared with the existing mainstream models. |
| first_indexed | 2024-04-09T22:58:22Z |
| format | Article |
| id | doaj.art-623f78a1f6634f1ebe49a958212589c9 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T22:58:22Z |
| publishDate | 2023-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-623f78a1f6634f1ebe49a958212589c92023-03-22T11:07:30ZengNature PortfolioScientific Reports2045-23222023-02-011311910.1038/s41598-023-30355-yNamed entity recognition for Chinese based on global pointer and adversarial trainingHongjun Li0Mingzhe Cheng1Zelin Yang2Liqun Yang3Yansong Chua4Key Laboratory of Deep-time Geography and Environment Reconstruction and Applications, MNR & College of Computer Science and Cyber Security, Chengdu University of TechnologyCollege of Computer Science and Cyber Security, Chengdu University of TechnologyCollege of Computer Science and Cyber Security, Chengdu University of TechnologyChina Nanhu Academy of Electronics and Information Technology CNAEITChina Nanhu Academy of Electronics and Information Technology CNAEITAbstract Named entity recognition aims to identify entities from unstructured text and is an important subtask for natural language processing and building knowledge graphs. Most of the existing entity recognition methods use conditional random fields as label decoders or use pointer networks for entity recognition. However, when the number of tags is large, the computational cost of method based on conditional random fields is high and the problem of nested entities cannot be solved. The pointer network uses two modules to identify the first and the last of the entities separately, and a single module can only focus on the information of the first or the last of the entities, but cannot pay attention to the global information of the entities. In addition, the neural network model has the problem of local instability. To solve mentioned problems, a named entity recognition model based on global pointer and adversarial training is proposed. To obtain global entity information, global pointer is used to decode entity information, and rotary relative position information is considered in the model designing to improve the model’s perception of position; to solve the model’s local instability problem, adversarial training is used to improve the robustness and generalization of the model. The experimental results show that the F1 score of the model are improved on several public datasets of OntoNotes5, MSRA, Resume, and Weibo compared with the existing mainstream models.https://doi.org/10.1038/s41598-023-30355-y |
| spellingShingle | Hongjun Li Mingzhe Cheng Zelin Yang Liqun Yang Yansong Chua Named entity recognition for Chinese based on global pointer and adversarial training Scientific Reports |
| title | Named entity recognition for Chinese based on global pointer and adversarial training |
| title_full | Named entity recognition for Chinese based on global pointer and adversarial training |
| title_fullStr | Named entity recognition for Chinese based on global pointer and adversarial training |
| title_full_unstemmed | Named entity recognition for Chinese based on global pointer and adversarial training |
| title_short | Named entity recognition for Chinese based on global pointer and adversarial training |
| title_sort | named entity recognition for chinese based on global pointer and adversarial training |
| url | https://doi.org/10.1038/s41598-023-30355-y |
| work_keys_str_mv | AT hongjunli namedentityrecognitionforchinesebasedonglobalpointerandadversarialtraining AT mingzhecheng namedentityrecognitionforchinesebasedonglobalpointerandadversarialtraining AT zelinyang namedentityrecognitionforchinesebasedonglobalpointerandadversarialtraining AT liqunyang namedentityrecognitionforchinesebasedonglobalpointerandadversarialtraining AT yansongchua namedentityrecognitionforchinesebasedonglobalpointerandadversarialtraining |