The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing

The Knowledge Graph Entity Typing (KGET) task aims to predict missing type annotations for entities in knowledge graphs. Recent works only utilize the $\mathit{\text{structural}}\mathit{\text{knowledge}}$ in the local neighborhood of entities, disregarding $\mathit{\text{semantic}}\mathit{\text{knowledge}}$ in the textual representations of entities, relations, and types that are also crucial for type inference. Additionally, we observe that the interaction between semantic and structural knowledge can be utilized to address the false-negative problem. In this paper, we propose a novel $\underset{‾}{\mathbf{\text{S}}}$emantic and $\underset{‾}{\mathbf{\text{S}}}$tructure-aware KG $\underset{‾}{\mathbf{\text{E}}}$ntity $\underset{‾}{\mathbf{\text{T}}}$yping~{(SSET)} framework, which is composed of three modules. First, the $\mathit{\text{Semantic}}\mathit{\text{Knowledge}}\mathit{\text{Encoding}}$ module encodes factual knowledge in the KG with a Masked Entity Typing task. Then, the $\mathit{\text{Structural}}\mathit{\text{Knowledge}}\mathit{\text{Aggregation}}$ module aggregates knowledge from the multi-hop neighborhood of entities to infer missing types. Finally, the $\mathit{\text{Unsupervised}}\mathit{\text{Type}}\mathit{\text{Re-ranking}}$ module utilizes the inference results from the two models above to generate type predictions that are robust to false-negative samples. Extensive experiments show that SSET significantly outperforms existing state-of-the-art methods.