Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction



Mandya, Angrosh, Bollegala, Danushka and Coenen, Frans
(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.

[thumbnail of coling_2020_submitted.pdf] Text
coling_2020_submitted.pdf - Author Accepted Manuscript

Download (622kB) | Preview

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 Jun 2024 02:02
DOI: 10.18653/v1/2020.coling-main.565
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3105989