StATIK: Structure and Text for Inductive Knowledge Graph Completion

Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Murali Annavaram, Aram Galstyan, Greg Ver Steeg


Abstract
Knowledge graphs (KGs) often represent knowledge bases that are incomplete. Machine learning models can alleviate this by helping automate graph completion. Recently, there has been growing interest in completing knowledge bases that are dynamic, where previously unseen entities may be added to the KG with many missing links. In this paper, we present StATIKStructure And Text for Inductive Knowledge Completion. StATIK uses Language Models to extract the semantic information from text descriptions, while using Message Passing Neural Networks to capture the structural information. StATIK achieves state of the art results on three challenging inductive baselines. We further analyze our hybrid model through detailed ablation studies.
Anthology ID:
2022.findings-naacl.46
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Venues:
Findings | NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
604–615
Language:
URL:
https://aclanthology.org/2022.findings-naacl.46
DOI:
10.18653/v1/2022.findings-naacl.46
Bibkey:
Cite (ACL):
Elan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Murali Annavaram, Aram Galstyan, and Greg Ver Steeg. 2022. StATIK: Structure and Text for Inductive Knowledge Graph Completion. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 604–615, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
StATIK: Structure and Text for Inductive Knowledge Graph Completion (Markowitz et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.46.pdf
Software:
 2022.findings-naacl.46.software.zip