Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer
The task of named entity recognition (NER) is to identify entities in the text and predict their categories. In real-life scenarios, the context of the text is often complex, and there may exist nested entities within an entity. This kind of entity is called a nested entity, and the task of recogniz...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Applied System Innovation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2571-5577/7/1/8 |
| _version_ | 1797298981577949184 |
|---|---|
| author | Weijun Li Jintong Liu Yuxiao Gao Xinyong Zhang Jianlai Gu |
| author_facet | Weijun Li Jintong Liu Yuxiao Gao Xinyong Zhang Jianlai Gu |
| author_sort | Weijun Li |
| collection | DOAJ |
| description | The task of named entity recognition (NER) is to identify entities in the text and predict their categories. In real-life scenarios, the context of the text is often complex, and there may exist nested entities within an entity. This kind of entity is called a nested entity, and the task of recognizing entities with nested structures is referred to as nested named entity recognition. Most existing NER models can only handle flat entities, and there has been limited research progress in Chinese nested named entity recognition, resulting in relatively few models in this direction. General NER models have limited semantic extraction capabilities and cannot capture deep semantic information between nested entities in the text. To address these issues, this paper proposes a model that uses the GlobalPointer module to identify nested entities in the text and constructs the IDCNNLR semantic extraction module to extract deep semantic information. Furthermore, multiple-head self-attention mechanisms are incorporated into the model at multiple positions to achieve data denoising, enhancing the quality of semantic features. The proposed model considers each possible entity boundary through the GlobalPointer module, and the IDCNNLR semantic extraction module and multi-position attention mechanism are introduced to enhance the model’s semantic extraction capability. Experimental results demonstrate that the proposed model achieves <i>F1</i> scores of 69.617% and 79.285% on the CMeEE Chinese nested entity recognition dataset and CLUENER2020 Chinese fine-grained entity recognition dataset, respectively. The model exhibits improvement compared to baseline models, and each innovation point shows effective performance enhancement in ablative experiments. |
| first_indexed | 2024-03-07T22:42:54Z |
| format | Article |
| id | doaj.art-b67970492f124d0a8571f60ac3c8aceb |
| institution | Directory Open Access Journal |
| issn | 2571-5577 |
| language | English |
| last_indexed | 2024-03-07T22:42:54Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied System Innovation |
| spelling | doaj.art-b67970492f124d0a8571f60ac3c8aceb2024-02-23T15:06:57ZengMDPI AGApplied System Innovation2571-55772024-01-0171810.3390/asi7010008Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointerWeijun Li0Jintong Liu1Yuxiao Gao2Xinyong Zhang3Jianlai Gu4School of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaSchool of Computer Science and Engineering, North Minzu University, Yinchuan 750021, ChinaThe task of named entity recognition (NER) is to identify entities in the text and predict their categories. In real-life scenarios, the context of the text is often complex, and there may exist nested entities within an entity. This kind of entity is called a nested entity, and the task of recognizing entities with nested structures is referred to as nested named entity recognition. Most existing NER models can only handle flat entities, and there has been limited research progress in Chinese nested named entity recognition, resulting in relatively few models in this direction. General NER models have limited semantic extraction capabilities and cannot capture deep semantic information between nested entities in the text. To address these issues, this paper proposes a model that uses the GlobalPointer module to identify nested entities in the text and constructs the IDCNNLR semantic extraction module to extract deep semantic information. Furthermore, multiple-head self-attention mechanisms are incorporated into the model at multiple positions to achieve data denoising, enhancing the quality of semantic features. The proposed model considers each possible entity boundary through the GlobalPointer module, and the IDCNNLR semantic extraction module and multi-position attention mechanism are introduced to enhance the model’s semantic extraction capability. Experimental results demonstrate that the proposed model achieves <i>F1</i> scores of 69.617% and 79.285% on the CMeEE Chinese nested entity recognition dataset and CLUENER2020 Chinese fine-grained entity recognition dataset, respectively. The model exhibits improvement compared to baseline models, and each innovation point shows effective performance enhancement in ablative experiments.https://www.mdpi.com/2571-5577/7/1/8named entity recognitionnatural language processingdeep neural networksfeature extractionknowledge graph |
| spellingShingle | Weijun Li Jintong Liu Yuxiao Gao Xinyong Zhang Jianlai Gu Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer Applied System Innovation named entity recognition natural language processing deep neural networks feature extraction knowledge graph |
| title | Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer |
| title_full | Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer |
| title_fullStr | Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer |
| title_full_unstemmed | Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer |
| title_short | Research on Chinese Nested Entity Recognition Based on IDCNNLR and GlobalPointer |
| title_sort | research on chinese nested entity recognition based on idcnnlr and globalpointer |
| topic | named entity recognition natural language processing deep neural networks feature extraction knowledge graph |
| url | https://www.mdpi.com/2571-5577/7/1/8 |
| work_keys_str_mv | AT weijunli researchonchinesenestedentityrecognitionbasedonidcnnlrandglobalpointer AT jintongliu researchonchinesenestedentityrecognitionbasedonidcnnlrandglobalpointer AT yuxiaogao researchonchinesenestedentityrecognitionbasedonidcnnlrandglobalpointer AT xinyongzhang researchonchinesenestedentityrecognitionbasedonidcnnlrandglobalpointer AT jianlaigu researchonchinesenestedentityrecognitionbasedonidcnnlrandglobalpointer |