Context-aware Entity Typing in Knowledge Graphs

Weiran Pan, Wei Wei, Xian-Ling Mao


Abstract
Knowledge graph entity typing aims to infer entities’ missing types in knowledge graphs which is an important but under-explored issue. This paper proposes a novel method for this task by utilizing entities’ contextual information. Specifically, we design two inference mechanisms: i) N2T: independently use each neighbor of an entity to infer its type; ii) Agg2T: aggregate the neighbors of an entity to infer its type. Those mechanisms will produce multiple inference results, and an exponentially weighted pooling method is used to generate the final inference result. Furthermore, we propose a novel loss function to alleviate the false-negative problem during training. Experiments on two real-world KGs demonstrate the effectiveness of our method. The source code and data of this paper can be obtained from https://github.com/CCIIPLab/CET.
Anthology ID:
2021.findings-emnlp.193
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2240–2250
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.193
DOI:
10.18653/v1/2021.findings-emnlp.193
Bibkey:
Cite (ACL):
Weiran Pan, Wei Wei, and Xian-Ling Mao. 2021. Context-aware Entity Typing in Knowledge Graphs. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2240–2250, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Context-aware Entity Typing in Knowledge Graphs (Pan et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/2021.findings-emnlp.193.pdf
Video:
 https://preview.aclanthology.org/author-url/2021.findings-emnlp.193.mp4
Code
 cciiplab/cet
Data
YAGO