Multi-Task Sequence Tagging for Denoised Causal Relation Extraction
Extracting causal relations from natural language texts is crucial for uncovering causality, and most existing causal relation extraction models are single-task learning-based models, which can not comprehensively address attributes such as part-of-speech tagging and chunk analysis. However, the cha...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/11/1737 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722517791440896 |
|---|---|
| author | Yijia Zhang Chaofan Liu Yuan Zhu Wanyu Chen |
| author_facet | Yijia Zhang Chaofan Liu Yuan Zhu Wanyu Chen |
| author_sort | Yijia Zhang |
| collection | DOAJ |
| description | Extracting causal relations from natural language texts is crucial for uncovering causality, and most existing causal relation extraction models are single-task learning-based models, which can not comprehensively address attributes such as part-of-speech tagging and chunk analysis. However, the characteristics of words with multi-domains are more relevant for causal relation extraction, due to words such as adjectives, linking verbs, etc., bringing more noise data limiting the effectiveness of the single-task-based learning methods. Furthermore, causalities from diverse domains also raise a challenge, as existing models tend to falter in multiple domains compared to a single one. In light of this, we propose a multi-task sequence tagging model, MPC−CE, which utilizes more information about causality and relevant tasks to improve causal relation extraction in noised data. By modeling auxiliary tasks, MPC−CE promotes a hierarchical understanding of linguistic structure and semantic roles, filtering noise and isolating salient entities. Furthermore, the sparse sharing paradigm extracts only the most broadly beneficial parameters by pruning redundant ones during training, enhancing model generalization. The empirical results on two datasets show 2.19% and 3.12% F1 improvement, respectively, compared to baselines, demonstrating that our proposed model can effectively enhance causal relation extraction with semantic features across multiple syntactic tasks, offering the representational power to overcome pervasive noise and cross-domain issues. |
| format | Article |
| id | doaj-art-67c4cf769d874916ba9fa026f59c00ec |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-67c4cf769d874916ba9fa026f59c00ec2025-08-20T03:11:19ZengMDPI AGMathematics2227-73902025-05-011311173710.3390/math13111737Multi-Task Sequence Tagging for Denoised Causal Relation ExtractionYijia Zhang0Chaofan Liu1Yuan Zhu2Wanyu Chen3College of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaCollege of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaCollege of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Electronic Countermeasures, National University of Defense Technology, Hefei 230037, ChinaExtracting causal relations from natural language texts is crucial for uncovering causality, and most existing causal relation extraction models are single-task learning-based models, which can not comprehensively address attributes such as part-of-speech tagging and chunk analysis. However, the characteristics of words with multi-domains are more relevant for causal relation extraction, due to words such as adjectives, linking verbs, etc., bringing more noise data limiting the effectiveness of the single-task-based learning methods. Furthermore, causalities from diverse domains also raise a challenge, as existing models tend to falter in multiple domains compared to a single one. In light of this, we propose a multi-task sequence tagging model, MPC−CE, which utilizes more information about causality and relevant tasks to improve causal relation extraction in noised data. By modeling auxiliary tasks, MPC−CE promotes a hierarchical understanding of linguistic structure and semantic roles, filtering noise and isolating salient entities. Furthermore, the sparse sharing paradigm extracts only the most broadly beneficial parameters by pruning redundant ones during training, enhancing model generalization. The empirical results on two datasets show 2.19% and 3.12% F1 improvement, respectively, compared to baselines, demonstrating that our proposed model can effectively enhance causal relation extraction with semantic features across multiple syntactic tasks, offering the representational power to overcome pervasive noise and cross-domain issues.https://www.mdpi.com/2227-7390/13/11/1737causal relation extractionsequence taggingmulti-task learning |
| spellingShingle | Yijia Zhang Chaofan Liu Yuan Zhu Wanyu Chen Multi-Task Sequence Tagging for Denoised Causal Relation Extraction Mathematics causal relation extraction sequence tagging multi-task learning |
| title | Multi-Task Sequence Tagging for Denoised Causal Relation Extraction |
| title_full | Multi-Task Sequence Tagging for Denoised Causal Relation Extraction |
| title_fullStr | Multi-Task Sequence Tagging for Denoised Causal Relation Extraction |
| title_full_unstemmed | Multi-Task Sequence Tagging for Denoised Causal Relation Extraction |
| title_short | Multi-Task Sequence Tagging for Denoised Causal Relation Extraction |
| title_sort | multi task sequence tagging for denoised causal relation extraction |
| topic | causal relation extraction sequence tagging multi-task learning |
| url | https://www.mdpi.com/2227-7390/13/11/1737 |
| work_keys_str_mv | AT yijiazhang multitasksequencetaggingfordenoisedcausalrelationextraction AT chaofanliu multitasksequencetaggingfordenoisedcausalrelationextraction AT yuanzhu multitasksequencetaggingfordenoisedcausalrelationextraction AT wanyuchen multitasksequencetaggingfordenoisedcausalrelationextraction |