Context-aware Entity Typing in Knowledge Graphs
This work addresses an under-explored issue in knowledge graph completion, providing incremental improvements for researchers and practitioners in semantic web and AI domains.
The paper tackles the problem of inferring missing entity types in knowledge graphs by proposing a context-aware method that uses neighbor-based inference mechanisms and a novel loss function to address false negatives, achieving effectiveness demonstrated on two real-world knowledge graphs.
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.