Stage-oe-small.jpg

Inproceedings3836: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
K
Zeile 19: Zeile 19:
 
|Organization=DL4KG@ESWC2020
 
|Organization=DL4KG@ESWC2020
 
|Publisher=CEUR
 
|Publisher=CEUR
 +
|Volume=2635
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
 +
|Abstract=Most Knowledge Graphs (KGs) contain textual descriptions of entities in various natural languages. These descriptions of entities provide valuable information that may not be explicitly represented in the structured part of the KG. Based on this fact, some link prediction methods which make use of the information presented in the textual descriptions of entities have been proposed to learn representations of (monolingual) KGs. However, these methods use entity descriptions in only one language and ignore the fact that descriptions given in differ- ent languages may provide complementary information and thereby also additional semantics. In this position paper, the problem of effectively leveraging multilingual entity descriptions for the purpose of link pre- diction in KGs will be discussed along with potential solutions to the problem.
 
|Link=http://ceur-ws.org/Vol-2635/paper7.pdf
 
|Link=http://ceur-ws.org/Vol-2635/paper7.pdf
 
|Forschungsgruppe=Information Service Engineering
 
|Forschungsgruppe=Information Service Engineering
 
}}
 
}}

Version vom 17. November 2022, 10:27 Uhr


Semantic Entity Enrichment by leveraging Multi-lingual Descriptions for Link Prediction


Semantic Entity Enrichment by leveraging Multi-lingual Descriptions for Link Prediction



Published: 2020 Juni

Buchtitel: Proceedings of International Workshop on Deep Learning for Knowledge Graphs
Ausgabe: 2635
Verlag: CEUR
Organisation: DL4KG∂ESWC2020

Referierte Veröffentlichung

BibTeX

Kurzfassung
Most Knowledge Graphs (KGs) contain textual descriptions of entities in various natural languages. These descriptions of entities provide valuable information that may not be explicitly represented in the structured part of the KG. Based on this fact, some link prediction methods which make use of the information presented in the textual descriptions of entities have been proposed to learn representations of (monolingual) KGs. However, these methods use entity descriptions in only one language and ignore the fact that descriptions given in differ- ent languages may provide complementary information and thereby also additional semantics. In this position paper, the problem of effectively leveraging multilingual entity descriptions for the purpose of link pre- diction in KGs will be discussed along with potential solutions to the problem.

Weitere Informationen unter: Link



Forschungsgruppe

Information Service Engineering


Forschungsgebiet