Entity Type Prediction Leveraging Graph Walks and Entity Descriptions
This work addresses the entity typing task for Knowledge Graphs like DBpedia and Freebase, which is incremental as it builds on existing RDF2vec techniques by integrating textual descriptions.
The paper tackles the problem of incomplete entity type information in Knowledge Graphs by proposing GRAND, a method that combines graph walks from RDF2vec with textual descriptions for entity typing, achieving superior performance over baselines on DBpedia and FIGER datasets for both fine-grained and coarse-grained classes.
The entity type information in Knowledge Graphs (KGs) such as DBpedia, Freebase, etc. is often incomplete due to automated generation or human curation. Entity typing is the task of assigning or inferring the semantic type of an entity in a KG. This paper presents \textit{GRAND}, a novel approach for entity typing leveraging different graph walk strategies in RDF2vec together with textual entity descriptions. RDF2vec first generates graph walks and then uses a language model to obtain embeddings for each node in the graph. This study shows that the walk generation strategy and the embedding model have a significant effect on the performance of the entity typing task. The proposed approach outperforms the baseline approaches on the benchmark datasets DBpedia and FIGER for entity typing in KGs for both fine-grained and coarse-grained classes. The results show that the combination of order-aware RDF2vec variants together with the contextual embeddings of the textual entity descriptions achieve the best results.