Stage-oe-small.jpg

Article3219: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
K
K
 
Zeile 22: Zeile 22:
 
|Volume=12
 
|Volume=12
 
|Number=4
 
|Number=4
 +
|Pages=617-647
 
|Publisher=IOS Press
 
|Publisher=IOS Press
 +
|Tags=Knowledge Graphs, Knowledge Graph Embeddings, Knowledge Graph Embeddings with Literals, Link Prediction, Survey
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
Zeile 28: Zeile 30:
 
|Download=swj2475.pdf
 
|Download=swj2475.pdf
 
|Link=https://arxiv.org/abs/1910.12507, http://www.semantic-web-journal.net/system/files/swj2475.pdf
 
|Link=https://arxiv.org/abs/1910.12507, http://www.semantic-web-journal.net/system/files/swj2475.pdf
 +
|DOI Name=10.3233/SW-200404
 
|Forschungsgruppe=Information Service Engineering
 
|Forschungsgruppe=Information Service Engineering
 
}}
 
}}

Aktuelle Version vom 17. November 2022, 08:31 Uhr


A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?


A Survey on Knowledge Graph Embeddings with Literals: Which model links better Literal-ly?



Veröffentlicht: 2020

Journal: Semantic Web Journal
Nummer: 4
Seiten: 617-647
Verlag: IOS Press
Volume: 12


Referierte Veröffentlichung

BibTeX

Tags:Knowledge GraphsKnowledge Graph EmbeddingsKnowledge Graph Embeddings with LiteralsLink PredictionSurvey


Kurzfassung
Knowledge Graphs (KGs) are composed of structured information about a particular domain in the form of entities and relations. In addition to the structured information KGs help in facilitating interconnectivity and interoperability between different resources represented in the Linked Data Cloud. KGs have been used in a variety of applications such as entity linking, question answering, recommender systems, etc. However, KG applications suffer from high computational and storage costs. Hence, there arises the necessity for a representation able to map the high dimensional KGs into low dimensional spaces, i.e., embedding space, preserving structural as well as relational information. This paper conducts a survey of KG embedding models which not only consider the structured information contained in the form of entities and relations in a KG but also its unstructured information represented as literals such as text, numerical values, images, etc. Along with a theoretical analysis and comparison of the methods proposed so far for generating KG embeddings with literals, an empirical evaluation of the different methods under identical settings has been performed for the general task of link prediction.

Download: Media:swj2475.pdf
Weitere Informationen unter: LinkLink
DOI Link: 10.3233/SW-200404



Forschungsgruppe

Information Service Engineering


Forschungsgebiet