Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism
Named Entity Recognition (NER) is one key step for constructing power domain knowledge graph which is increasingly urgent in building smart grid. This paper proposes a new NER model called Att-CNN-BiGRU-CRF which consists of the following five layers. The prefix Att means the model is based on atten...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9585441/ |
| _version_ | 1818424982289514496 |
|---|---|
| author | Kaihong Zheng Lingyun Sun Xin Wang Shangli Zhou Hanbin Li Sheng Li Lukun Zeng Qihang Gong |
| author_facet | Kaihong Zheng Lingyun Sun Xin Wang Shangli Zhou Hanbin Li Sheng Li Lukun Zeng Qihang Gong |
| author_sort | Kaihong Zheng |
| collection | DOAJ |
| description | Named Entity Recognition (NER) is one key step for constructing power domain knowledge graph which is increasingly urgent in building smart grid. This paper proposes a new NER model called Att-CNN-BiGRU-CRF which consists of the following five layers. The prefix Att means the model is based on attention mechanism. A joint feature embedding layer combines the character embedding and word embedding based on BERT to obtain more semantic information. A convolutional attention layer combines the local attention mechanism and CNN to capture the relationship of local context. A BiGRU layer extracts higher-level features of power metering text. A global multi-head attention layer optimizes the processing of sentence level information. A CRF layer obtains the output tag sequences. This paper also constructs a corresponding power metering corpus data set with a new entity classification method. The novelties of our work are the five layer model structure and the attention mechanism. Experimental results show that the proposed model has high recall rate 88.16% and precision rate 89.33% which is better than the state-of-the-art models. |
| first_indexed | 2024-12-14T14:06:41Z |
| format | Article |
| id | doaj.art-9b0ead4904514bc99ac9df450241d6f9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T14:06:41Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9b0ead4904514bc99ac9df450241d6f92022-12-21T22:58:30ZengIEEEIEEE Access2169-35362021-01-01915256415257310.1109/ACCESS.2021.31231549585441Named Entity Recognition in Electric Power Metering Domain Based on Attention MechanismKaihong Zheng0Lingyun Sun1Xin Wang2https://orcid.org/0000-0002-4134-0613Shangli Zhou3Hanbin Li4Sheng Li5Lukun Zeng6Qihang Gong7Digital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, ChinaDigital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaCollege of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, Zhejiang, ChinaDigital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaDigital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaDigital Grid Research Institute, China Southern Power Grid, Guangzhou, Guangdong, ChinaNamed Entity Recognition (NER) is one key step for constructing power domain knowledge graph which is increasingly urgent in building smart grid. This paper proposes a new NER model called Att-CNN-BiGRU-CRF which consists of the following five layers. The prefix Att means the model is based on attention mechanism. A joint feature embedding layer combines the character embedding and word embedding based on BERT to obtain more semantic information. A convolutional attention layer combines the local attention mechanism and CNN to capture the relationship of local context. A BiGRU layer extracts higher-level features of power metering text. A global multi-head attention layer optimizes the processing of sentence level information. A CRF layer obtains the output tag sequences. This paper also constructs a corresponding power metering corpus data set with a new entity classification method. The novelties of our work are the five layer model structure and the attention mechanism. Experimental results show that the proposed model has high recall rate 88.16% and precision rate 89.33% which is better than the state-of-the-art models.https://ieeexplore.ieee.org/document/9585441/Power meteringattention mechanismjoint featurenamed entity recognition |
| spellingShingle | Kaihong Zheng Lingyun Sun Xin Wang Shangli Zhou Hanbin Li Sheng Li Lukun Zeng Qihang Gong Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism IEEE Access Power metering attention mechanism joint feature named entity recognition |
| title | Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism |
| title_full | Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism |
| title_fullStr | Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism |
| title_full_unstemmed | Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism |
| title_short | Named Entity Recognition in Electric Power Metering Domain Based on Attention Mechanism |
| title_sort | named entity recognition in electric power metering domain based on attention mechanism |
| topic | Power metering attention mechanism joint feature named entity recognition |
| url | https://ieeexplore.ieee.org/document/9585441/ |
| work_keys_str_mv | AT kaihongzheng namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT lingyunsun namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT xinwang namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT shanglizhou namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT hanbinli namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT shengli namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT lukunzeng namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism AT qihanggong namedentityrecognitioninelectricpowermeteringdomainbasedonattentionmechanism |