Mandya, Angrosh, Bollegala, Danushka and Coenen, Frans
(2020)
Contextualised Graph Attention for Improved Relation Extraction.
CoRR, abs/20.
|
Text
2004.10624v1.pdf - Submitted version Download (447kB) | Preview |
Abstract
This paper presents a contextualized graph attention network that combines edge features and multiple sub-graphs for improving relation extraction. A novel method is proposed to use multiple sub-graphs to learn rich node representations in graph-based networks. To this end multiple sub-graphs are obtained from a single dependency tree. Two types of edge features are proposed, which are effectively combined with GAT and GCN models to apply for relation extraction. The proposed model achieves state-of-the-art performance on Semeval 2010 Task 8 dataset, achieving an F1-score of 86.3.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | cs.CL, cs.CL, cs.IR |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 30 Apr 2020 10:36 |
| Last Modified: | 18 Jan 2023 23:53 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3085262 |
Share
Share
