Inproceedings3735: Unterschied zwischen den Versionen
Bh7169 (Diskussion | Beiträge) (Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Biswas |ErsterAutorVorname=Russa }} {{Publikation Author |Rank=2 |Author=Maria Koutraki }} {{Publikation Author…“) |
Xi5455 (Diskussion | Beiträge) K |
||
Zeile 23: | Zeile 23: | ||
{{Publikation Details | {{Publikation Details | ||
|Abstract=Wikipedia has emerged as the largest multilingual, web based general reference work on the Internet. A huge amount of human resources have been invested in the creation and update of Wikipedia articles which are ideally complemented by so-called infobox templates defining the type of the underlying article. It has been observed that the Wikipedia infobox type information is often incomplete and inconsistent due to various reasons. However, the Wikipedia infobox type information plays a fundamental role for the RDF type information of Wikipedia based Knowledge Graphs such as DBpedia. This stimulates the need of always having the correct and complete infobox type information. In this work, we propose an approach to predict Wikipedia infobox types by using word embeddings on categories of Wikipedia articles, and analyze the impact of using minimal information from the Wikipedia articles in the prediction process. | |Abstract=Wikipedia has emerged as the largest multilingual, web based general reference work on the Internet. A huge amount of human resources have been invested in the creation and update of Wikipedia articles which are ideally complemented by so-called infobox templates defining the type of the underlying article. It has been observed that the Wikipedia infobox type information is often incomplete and inconsistent due to various reasons. However, the Wikipedia infobox type information plays a fundamental role for the RDF type information of Wikipedia based Knowledge Graphs such as DBpedia. This stimulates the need of always having the correct and complete infobox type information. In this work, we propose an approach to predict Wikipedia infobox types by using word embeddings on categories of Wikipedia articles, and analyze the impact of using minimal information from the Wikipedia articles in the prediction process. | ||
+ | |Download=ekaw-poster-27.pdf | ||
|Link=http://ceur-ws.org/Vol-2262/ekaw-poster-27.pdf | |Link=http://ceur-ws.org/Vol-2262/ekaw-poster-27.pdf | ||
|Forschungsgruppe=Information Service Engineering | |Forschungsgruppe=Information Service Engineering | ||
}} | }} |
Aktuelle Version vom 17. November 2022, 15:57 Uhr
Predicting Wikipedia Infobox Type Information using Word Embeddings on Categories
Predicting Wikipedia Infobox Type Information using Word Embeddings on Categories
Published: 2018
Dezember
Buchtitel: Proc. 21st International Conference on Knowledge Engineering and Knowledge Management 2018 (EKAW 2018)
Nummer: 2262
Seiten: 29-31
Verlag: CEUR Workshop Proceedings
Referierte Veröffentlichung
BibTeX
Kurzfassung
Wikipedia has emerged as the largest multilingual, web based general reference work on the Internet. A huge amount of human resources have been invested in the creation and update of Wikipedia articles which are ideally complemented by so-called infobox templates defining the type of the underlying article. It has been observed that the Wikipedia infobox type information is often incomplete and inconsistent due to various reasons. However, the Wikipedia infobox type information plays a fundamental role for the RDF type information of Wikipedia based Knowledge Graphs such as DBpedia. This stimulates the need of always having the correct and complete infobox type information. In this work, we propose an approach to predict Wikipedia infobox types by using word embeddings on categories of Wikipedia articles, and analyze the impact of using minimal information from the Wikipedia articles in the prediction process.
Download: Media:ekaw-poster-27.pdf
Weitere Informationen unter: Link
Information Service Engineering