KIT | KIT-Bibliothek | Impressum | Datenschutz

Entity Type Prediction Leveraging Graph Walks and Entity Descriptions

Biswas, Russa ORCID iD icon; Portisch, Jan; Paulheim, Heiko; Sack, Harald 1; Alam, Mehwish
1 Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB), Karlsruher Institut für Technologie (KIT)

Abstract:

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.


Volltext §
DOI: 10.5445/IR/1000150523
Veröffentlicht am 28.04.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Forschungsbericht/Preprint
Publikationsdatum 29.07.2022
Sprache Englisch
Identifikator KITopen-ID: 1000150523
Bemerkung zur Veröffentlichung In: The 21st International Semantic Web Conference (ISWC 2022), virtual, 23–27 October 2022, Hangzhou, China
Schlagwörter Entity Type Prediction · RDF2vec · Knowledge Graph Embedding · Graph Walks · Language Models
Nachgewiesen in arXiv
Dimensions
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page