A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction
Relationship extraction is a crucial step in the construction of a knowledge graph. In this research, the grid field entity relationship extraction was performed via a labeling approach that used span representation. The subject entity and object entity were used as training instances to bolster the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/19/11074 |
| _version_ | 1827722691502669824 |
|---|---|
| author | Qi Meng Xixiang Zhang Yun Dong Yan Chen Dezhao Lin |
| author_facet | Qi Meng Xixiang Zhang Yun Dong Yan Chen Dezhao Lin |
| author_sort | Qi Meng |
| collection | DOAJ |
| description | Relationship extraction is a crucial step in the construction of a knowledge graph. In this research, the grid field entity relationship extraction was performed via a labeling approach that used span representation. The subject entity and object entity were used as training instances to bolster the linkage between them. The embedding layer of the RoBERTa pre-training model included word embedding, position embedding, and paragraph embedding information. In addition, semantic dependency was introduced to establish an effective linkage between different entities. To facilitate the effective linkage, an additional lexically labeled embedment was introduced to empower the model to acquire more profound semantic insights. After obtaining the embedding layer, the RoBERTa model was used for multi-task learning of entities and relations. The multi-task information was then fused using the parameter hard sharing mechanism. Finally, after the layer was fully connected, the predicted entity relations were obtained. The approach was tested on a grid field dataset created for this study. The obtained results demonstrated that the proposed model has high performance. |
| first_indexed | 2024-03-10T21:48:33Z |
| format | Article |
| id | doaj.art-570f362b86b746629cb9de48d5f6b97e |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T21:48:33Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-570f362b86b746629cb9de48d5f6b97e2023-11-19T14:08:21ZengMDPI AGApplied Sciences2076-34172023-10-0113191107410.3390/app131911074A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational ExtractionQi Meng0Xixiang Zhang1Yun Dong2Yan Chen3Dezhao Lin4Guangxi Power Grid Co., Ltd., Nanning 530022, ChinaGuangxi Power Grid Co., Ltd., Nanning 530022, ChinaGuangxi Power Grid Co., Ltd., Nanning 530022, ChinaSchool of Computer and Electronic Information, Guangxi University, Nanning 530004, ChinaSchool of Computer and Electronic Information, Guangxi University, Nanning 530004, ChinaRelationship extraction is a crucial step in the construction of a knowledge graph. In this research, the grid field entity relationship extraction was performed via a labeling approach that used span representation. The subject entity and object entity were used as training instances to bolster the linkage between them. The embedding layer of the RoBERTa pre-training model included word embedding, position embedding, and paragraph embedding information. In addition, semantic dependency was introduced to establish an effective linkage between different entities. To facilitate the effective linkage, an additional lexically labeled embedment was introduced to empower the model to acquire more profound semantic insights. After obtaining the embedding layer, the RoBERTa model was used for multi-task learning of entities and relations. The multi-task information was then fused using the parameter hard sharing mechanism. Finally, after the layer was fully connected, the predicted entity relations were obtained. The approach was tested on a grid field dataset created for this study. The obtained results demonstrated that the proposed model has high performance.https://www.mdpi.com/2076-3417/13/19/11074grid fieldrelational extractionRoBERTasemantic dependencylexical embedding |
| spellingShingle | Qi Meng Xixiang Zhang Yun Dong Yan Chen Dezhao Lin A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction Applied Sciences grid field relational extraction RoBERTa semantic dependency lexical embedding |
| title | A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction |
| title_full | A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction |
| title_fullStr | A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction |
| title_full_unstemmed | A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction |
| title_short | A Combined Semantic Dependency and Lexical Embedding RoBERTa Model for Grid Field Relational Extraction |
| title_sort | combined semantic dependency and lexical embedding roberta model for grid field relational extraction |
| topic | grid field relational extraction RoBERTa semantic dependency lexical embedding |
| url | https://www.mdpi.com/2076-3417/13/19/11074 |
| work_keys_str_mv | AT qimeng acombinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT xixiangzhang acombinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT yundong acombinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT yanchen acombinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT dezhaolin acombinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT qimeng combinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT xixiangzhang combinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT yundong combinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT yanchen combinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction AT dezhaolin combinedsemanticdependencyandlexicalembeddingrobertamodelforgridfieldrelationalextraction |