Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction

Mandya, Angrosh, Bollegala, Danushka ORCID: 0000-0003-4476-7003 and Coenen, Frans ORCID: 0000-0003-1026-6649 (2020) Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction. In: Proceedings of the 28th International Conference on Computational Linguistics, 2020-12 - 2020-12.

Text
coling_2020_submitted.pdf - Author Accepted Manuscript
Download (622kB) | Preview

Official URL: http://dx.doi.org/10.18653/v1/2020.coling-main.565

Abstract

We propose in this paper a contextualised graph convolution network over multiple dependency sub-graphs for relation extraction. A novel method to construct multiple sub-graphs using words in shortest dependency path and words linked to entities in the dependency graph is proposed. Graph convolution operation is performed over the resulting multiple sub-graphs to obtain more informative features useful for relation extraction. Our experimental results show that the proposed method achieves superior performance over existing GCN-based models achieving state-of-the-art performance on cross-sentence n-ary relation extraction and SemEval 2010 Task 8 sentence-level relation extraction task. Our model also achieves a comparable performance to the SoTA on the TACRED dataset.

Item Type:	Conference or Workshop Item (Unspecified)
Depositing User:	Symplectic Admin
Date Deposited:	04 Nov 2020 10:47
Last Modified:	15 Mar 2024 01:02
DOI:	10.18653/v1/2020.coling-main.565
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3105989