Relational prompt-based single-module single-step model for relational triple extraction
The relational triple extraction is a fundamental and essential information extraction task. The existing approaches of relation triple extraction achieve considerable performance but still suffer from 1) treating the relation between entities as a meaningless label while ignoring the relational sem...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823003026 |
| _version_ | 1797629713150115840 |
|---|---|
| author | Zhi Zhang Hui Liu Junan Yang Xiaoshuai Li |
| author_facet | Zhi Zhang Hui Liu Junan Yang Xiaoshuai Li |
| author_sort | Zhi Zhang |
| collection | DOAJ |
| description | The relational triple extraction is a fundamental and essential information extraction task. The existing approaches of relation triple extraction achieve considerable performance but still suffer from 1) treating the relation between entities as a meaningless label while ignoring the relational semantic information of the relation itself and 2) ignoring the interdependence and inseparability of three elements of the triple. To address these problems, this paper proposes a Relational Prompt approach, based on which constructs a Single-module Single-step relational triple extraction model (RPSS). In particular, the proposed relational prompt approach consist of a relational hard-prompt and a relational soft-prompt, while provide take into account different level of relational semantic information, covering both the token-level and the feature-level relational prompt information. Then, we jointly encode entities and relational prompts to obtain a unified global representation. We mine deep correlations between different embeddings through attention mechanism and then construct a triple interaction matrix. Then, all triples could be directly extracted from a single module in a single step. Experiments demonstrate the effectiveness of the relational prompt approach, as well as relational semantics and triple integrity are essential for relation extraction. Experimental results on two benchmark datasets demonstrate our model outperforms current state-of-the-art models. |
| first_indexed | 2024-03-11T10:57:57Z |
| format | Article |
| id | doaj.art-24c2e4e3b0a844f68c375e697eab1a6b |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-11T10:57:57Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-24c2e4e3b0a844f68c375e697eab1a6b2023-11-13T04:08:57ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-10-01359101748Relational prompt-based single-module single-step model for relational triple extractionZhi Zhang0Hui Liu1Junan Yang2Xiaoshuai Li3College of Electronic Engineering, National University of Defense Technology, Hefei 230037, ChinaCollege of Electronic Engineering, National University of Defense Technology, Hefei 230037, ChinaCorresponding author.; College of Electronic Engineering, National University of Defense Technology, Hefei 230037, ChinaCollege of Electronic Engineering, National University of Defense Technology, Hefei 230037, ChinaThe relational triple extraction is a fundamental and essential information extraction task. The existing approaches of relation triple extraction achieve considerable performance but still suffer from 1) treating the relation between entities as a meaningless label while ignoring the relational semantic information of the relation itself and 2) ignoring the interdependence and inseparability of three elements of the triple. To address these problems, this paper proposes a Relational Prompt approach, based on which constructs a Single-module Single-step relational triple extraction model (RPSS). In particular, the proposed relational prompt approach consist of a relational hard-prompt and a relational soft-prompt, while provide take into account different level of relational semantic information, covering both the token-level and the feature-level relational prompt information. Then, we jointly encode entities and relational prompts to obtain a unified global representation. We mine deep correlations between different embeddings through attention mechanism and then construct a triple interaction matrix. Then, all triples could be directly extracted from a single module in a single step. Experiments demonstrate the effectiveness of the relational prompt approach, as well as relational semantics and triple integrity are essential for relation extraction. Experimental results on two benchmark datasets demonstrate our model outperforms current state-of-the-art models.http://www.sciencedirect.com/science/article/pii/S1319157823003026Nature language processInformation extractionRelational triple extractionPrompt learningAttention mechanismRelational semantic |
| spellingShingle | Zhi Zhang Hui Liu Junan Yang Xiaoshuai Li Relational prompt-based single-module single-step model for relational triple extraction Journal of King Saud University: Computer and Information Sciences Nature language process Information extraction Relational triple extraction Prompt learning Attention mechanism Relational semantic |
| title | Relational prompt-based single-module single-step model for relational triple extraction |
| title_full | Relational prompt-based single-module single-step model for relational triple extraction |
| title_fullStr | Relational prompt-based single-module single-step model for relational triple extraction |
| title_full_unstemmed | Relational prompt-based single-module single-step model for relational triple extraction |
| title_short | Relational prompt-based single-module single-step model for relational triple extraction |
| title_sort | relational prompt based single module single step model for relational triple extraction |
| topic | Nature language process Information extraction Relational triple extraction Prompt learning Attention mechanism Relational semantic |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823003026 |
| work_keys_str_mv | AT zhizhang relationalpromptbasedsinglemodulesinglestepmodelforrelationaltripleextraction AT huiliu relationalpromptbasedsinglemodulesinglestepmodelforrelationaltripleextraction AT junanyang relationalpromptbasedsinglemodulesinglestepmodelforrelationaltripleextraction AT xiaoshuaili relationalpromptbasedsinglemodulesinglestepmodelforrelationaltripleextraction |