A domain semantics-enhanced relation extraction model for identifying the railway safety risk
Abstract The identification of railway safety risk is important in ensuring continuous and stable railway operations. Most works fail to consider the important relation between detected objects. In addition, poor domain semantics directly degrades the final performance due to difficulty in understan...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-05-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-023-01075-7 |
| _version_ | 1827780999612727296 |
|---|---|
| author | Youwei Wang Chengying Zhu Qiang Guo Yangdong Ye |
| author_facet | Youwei Wang Chengying Zhu Qiang Guo Yangdong Ye |
| author_sort | Youwei Wang |
| collection | DOAJ |
| description | Abstract The identification of railway safety risk is important in ensuring continuous and stable railway operations. Most works fail to consider the important relation between detected objects. In addition, poor domain semantics directly degrades the final performance due to difficulty in understanding railway text. To solve these challenging issues, we introduce the triple knowledge from knowledge graph to model the railway safety risk with the knowledge interconnection mode. Afterward, we recast the identification of railway safety risk as the relation extraction task, and propose a novel and effective Domain Semantics-Enhanced Relation Extraction (DSERE) model. Specifically, we design a domain semantics-enhanced transformer mechanism that automatically enhances the railway semantics from a dedicated railway lexicon. We further introduce piece-wise convolution neural networks to explore the fine-grained features contained in the structure of triple knowledge. With the domain semantics and fine-grained features, our model can fully understand the domain text and thus improve the performance of relation classification. Finally, the DSERE model is used to identify the railway safety risk of south zone of China Railway, and achieves 81.84% AUC and 76.00% F1 scores on the real-world dataset showing the superiority of our proposed model. |
| first_indexed | 2024-03-11T15:12:44Z |
| format | Article |
| id | doaj.art-5c60a99c4e334d97b07ab6b379688ff7 |
| institution | Directory Open Access Journal |
| issn | 2199-4536 2198-6053 |
| language | English |
| last_indexed | 2024-03-11T15:12:44Z |
| publishDate | 2023-05-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj.art-5c60a99c4e334d97b07ab6b379688ff72023-10-29T12:41:09ZengSpringerComplex & Intelligent Systems2199-45362198-60532023-05-01966493650710.1007/s40747-023-01075-7A domain semantics-enhanced relation extraction model for identifying the railway safety riskYouwei Wang0Chengying Zhu1Qiang Guo2Yangdong Ye3School of Computer and Artificial Intelligence, Zhengzhou UniversitySchool of Cyber Science and Engineering, Zhengzhou UniversitySchool of Computer and Artificial Intelligence, Zhengzhou UniversitySchool of Computer and Artificial Intelligence, Zhengzhou UniversityAbstract The identification of railway safety risk is important in ensuring continuous and stable railway operations. Most works fail to consider the important relation between detected objects. In addition, poor domain semantics directly degrades the final performance due to difficulty in understanding railway text. To solve these challenging issues, we introduce the triple knowledge from knowledge graph to model the railway safety risk with the knowledge interconnection mode. Afterward, we recast the identification of railway safety risk as the relation extraction task, and propose a novel and effective Domain Semantics-Enhanced Relation Extraction (DSERE) model. Specifically, we design a domain semantics-enhanced transformer mechanism that automatically enhances the railway semantics from a dedicated railway lexicon. We further introduce piece-wise convolution neural networks to explore the fine-grained features contained in the structure of triple knowledge. With the domain semantics and fine-grained features, our model can fully understand the domain text and thus improve the performance of relation classification. Finally, the DSERE model is used to identify the railway safety risk of south zone of China Railway, and achieves 81.84% AUC and 76.00% F1 scores on the real-world dataset showing the superiority of our proposed model.https://doi.org/10.1007/s40747-023-01075-7Railway safety riskRelation extractionDomain semanticsDomain semantics-enhanced transformer |
| spellingShingle | Youwei Wang Chengying Zhu Qiang Guo Yangdong Ye A domain semantics-enhanced relation extraction model for identifying the railway safety risk Complex & Intelligent Systems Railway safety risk Relation extraction Domain semantics Domain semantics-enhanced transformer |
| title | A domain semantics-enhanced relation extraction model for identifying the railway safety risk |
| title_full | A domain semantics-enhanced relation extraction model for identifying the railway safety risk |
| title_fullStr | A domain semantics-enhanced relation extraction model for identifying the railway safety risk |
| title_full_unstemmed | A domain semantics-enhanced relation extraction model for identifying the railway safety risk |
| title_short | A domain semantics-enhanced relation extraction model for identifying the railway safety risk |
| title_sort | domain semantics enhanced relation extraction model for identifying the railway safety risk |
| topic | Railway safety risk Relation extraction Domain semantics Domain semantics-enhanced transformer |
| url | https://doi.org/10.1007/s40747-023-01075-7 |
| work_keys_str_mv | AT youweiwang adomainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT chengyingzhu adomainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT qiangguo adomainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT yangdongye adomainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT youweiwang domainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT chengyingzhu domainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT qiangguo domainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk AT yangdongye domainsemanticsenhancedrelationextractionmodelforidentifyingtherailwaysafetyrisk |