KIT | KIT-Bibliothek | Impressum | Datenschutz

Leveraging literals for knowledge graph embeddings

Gesese, Genet Asefa


Nowadays, Knowledge Graphs (KGs) have become invaluable for various applications such as named entity recognition, entity linking, question answering. However, there is a huge computational and storage cost associated with these KG-based applications. Therefore, there arises the necessity of transforming the high dimensional KGs into low dimensional vector spaces, i.e., learning representations for the KGs. Since a KG represents facts in the form of interrelations between entities and also using attributes of entities, the semantics present in both forms should be preserved while transforming the KG into a vector space. Hence, the main focus of this thesis is to deal with the multimodality and multilinguality of literals when utilizing them for the representation learning of KGs. The other task is to extract benchmark datasets with a high level of difficulty for tasks such as link prediction and triple classification. These datasets could be used for evaluating both kind of KG Embeddings, those using literals and those which do not include literals.

Verlagsausgabe §
DOI: 10.5445/IR/1000141527
Veröffentlicht am 23.12.2021
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Angewandte Informatik und Formale Beschreibungsverfahren (AIFB)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2021
Sprache Englisch
Identifikator ISSN: 1613-0073
KITopen-ID: 1000141527
Erschienen in Proceedings of the Doctoral Consortium at ISWC 2021, co-located with 20th International Semantic Web Conference (ISWC 2021). Ed.: V. Tamma
Veranstaltung Doctoral Consortium at ISWC (ISWC-DC 2021), Online, 25.10.2021
Seiten 9-16
Serie CEUR Workshop Proceedings ; 3005
Externe Relationen Abstract/Volltext
Schlagwörter Knowledge Graph Embedding; Knowledge Graph Completion; Link Prediction; Literals ; Benchmark Datasets
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page