Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction

Angrosh Mandya, Danushka Bollegala, Frans Coenen


Abstract
We propose a contextualised graph convolution network over multiple dependency-based 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 parse 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 the existing GCN-based models achieving state-of-the-art performance on cross-sentence n-ary relation extraction dataset and SemEval 2010 Task 8 sentence-level relation extraction dataset. Our model also achieves a comparable performance to the SoTA on the TACRED dataset.
Anthology ID:
2020.coling-main.565
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
6424–6435
Language:
URL:
https://aclanthology.org/2020.coling-main.565
DOI:
10.18653/v1/2020.coling-main.565
Bibkey:
Cite (ACL):
Angrosh Mandya, Danushka Bollegala, and Frans Coenen. 2020. Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction. In Proceedings of the 28th International Conference on Computational Linguistics, pages 6424–6435, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction (Mandya et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.565.pdf
Data
SemEval-2010 Task-8TACRED