Transformer-based Entity Typing in Knowledge Graphs
This work addresses entity typing in knowledge graphs, which is important for improving knowledge representation and reasoning in AI systems, but it appears incremental as it builds on existing transformer architectures with specific adaptations.
The paper tackles the knowledge graph entity typing task by proposing a Transformer-based Entity Typing (TET) approach that encodes neighbor information through local, global, and context transformers, and it demonstrates superior performance on two real-world datasets compared to state-of-the-art methods.
We investigate the knowledge graph entity typing task which aims at inferring plausible entity types. In this paper, we propose a novel Transformer-based Entity Typing (TET) approach, effectively encoding the content of neighbors of an entity. More precisely, TET is composed of three different mechanisms: a local transformer allowing to infer missing types of an entity by independently encoding the information provided by each of its neighbors; a global transformer aggregating the information of all neighbors of an entity into a single long sequence to reason about more complex entity types; and a context transformer integrating neighbors content based on their contribution to the type inference through information exchange between neighbor pairs. Furthermore, TET uses information about class membership of types to semantically strengthen the representation of an entity. Experiments on two real-world datasets demonstrate the superior performance of TET compared to the state-of-the-art.