Few-shot Continual Relation Extraction via Open Information Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917935845474304 |
|---|---|
| author | Nguyen, Thiem Nguyen, Anh Tran, Quyen Vu, Tu Nguyen, Diep Ngo, Linh Nguyen, Thien |
| author_facet | Nguyen, Thiem Nguyen, Anh Tran, Quyen Vu, Tu Nguyen, Diep Ngo, Linh Nguyen, Thien |
| contents | Typically, Few-shot Continual Relation Extraction (FCRE) models must balance retaining prior knowledge while adapting to new tasks with extremely limited data. However, real-world scenarios may also involve unseen or undetermined relations that existing methods still struggle to handle. To address these challenges, we propose a novel approach that leverages the Open Information Extraction concept of Knowledge Graph Construction (KGC). Our method not only exposes models to all possible pairs of relations, including determined and undetermined labels not available in the training set, but also enriches model knowledge with diverse relation descriptions, thereby enhancing knowledge retention and adaptability in this challenging scenario. In the perspective of KGC, this is the first work explored in the setting of Continual Learning, allowing efficient expansion of the graph as the data evolves. Experimental results demonstrate our superior performance compared to other state-of-the-art FCRE baselines, as well as the efficiency in handling dynamic graph construction in this setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16648 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Few-shot Continual Relation Extraction via Open Information Extraction Nguyen, Thiem Nguyen, Anh Tran, Quyen Vu, Tu Nguyen, Diep Ngo, Linh Nguyen, Thien Machine Learning Artificial Intelligence Computation and Language Information Retrieval Typically, Few-shot Continual Relation Extraction (FCRE) models must balance retaining prior knowledge while adapting to new tasks with extremely limited data. However, real-world scenarios may also involve unseen or undetermined relations that existing methods still struggle to handle. To address these challenges, we propose a novel approach that leverages the Open Information Extraction concept of Knowledge Graph Construction (KGC). Our method not only exposes models to all possible pairs of relations, including determined and undetermined labels not available in the training set, but also enriches model knowledge with diverse relation descriptions, thereby enhancing knowledge retention and adaptability in this challenging scenario. In the perspective of KGC, this is the first work explored in the setting of Continual Learning, allowing efficient expansion of the graph as the data evolves. Experimental results demonstrate our superior performance compared to other state-of-the-art FCRE baselines, as well as the efficiency in handling dynamic graph construction in this setting. |
| title | Few-shot Continual Relation Extraction via Open Information Extraction |
| topic | Machine Learning Artificial Intelligence Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2502.16648 |