Edge: Enriching Knowledge Graph Embeddings with External Text

Saed Rezayi, Handong Zhao, Sungchul Kim, Ryan Rossi, Nedim Lipka, Sheng Li


Abstract
Knowledge graphs suffer from sparsity which degrades the quality of representations generated by various methods. While there is an abundance of textual information throughout the web and many existing knowledge bases, aligning information across these diverse data sources remains a challenge in the literature. Previous work has partially addressed this issue by enriching knowledge graph entities based on “hard” co-occurrence of words present in the entities of the knowledge graphs and external text, while we achieve “soft” augmentation by proposing a knowledge graph enrichment and embedding framework named Edge. Given an original knowledge graph, we first generate a rich but noisy augmented graph using external texts in semantic and structural level. To distill the relevant knowledge and suppress the introduced noise, we design a graph alignment term in a shared embedding space between the original graph and augmented graph. To enhance the embedding learning on the augmented graph, we further regularize the locality relationship of target entity based on negative sampling. Experimental results on four benchmark datasets demonstrate the robustness and effectiveness of Edge in link prediction and node classification.
Anthology ID:
2021.naacl-main.221
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2767–2776
Language:
URL:
https://aclanthology.org/2021.naacl-main.221
DOI:
10.18653/v1/2021.naacl-main.221
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.221.pdf