Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network

Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth, Jill Fain Lehman, Carolyn Rosé


Abstract
Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include biomedical and encyclopedic knowledge and use an existing commonsense KG dataset to explore KG completion in the more realistic setting where dense connectivity is not guaranteed. We develop a deep convolutional network that utilizes textual entity representations and demonstrate that our model outperforms recent KG completion methods in this challenging setting. We find that our model’s performance improvements stem primarily from its robustness to sparsity. We then distill the knowledge from the convolutional network into a student network that re-ranks promising candidate entities. This re-ranking stage leads to further improvements in performance and demonstrates the effectiveness of entity re-ranking for KG completion.
Anthology ID:
2021.acl-long.82
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1016–1029
Language:
URL:
https://aclanthology.org/2021.acl-long.82
DOI:
10.18653/v1/2021.acl-long.82
Bibkey:
Cite (ACL):
Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth, Jill Fain Lehman, and Carolyn Rosé. 2021. Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1016–1029, Online. Association for Computational Linguistics.
Cite (Informal):
Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network (Lovelace et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.82.pdf
Video:
 https://aclanthology.org/2021.acl-long.82.mp4
Code
 justinlovelace/robust-kg-completion
Data
FB15k-237