Wikipedia, the multilingual, free content encyclopedia has
evolved as the largest and the most popular general reference work on the
Internet. Since the time of commencement of Wikipedia, crowd sourcing
of articles has been one of the most salient features of this open encyclo-
pedia. It is obvious that enormous amount of work and expertise goes in
the creation of a self-content article. However, it has been observed that
the infobox type information in Wikipedia articles is often incomplete,
incorrect and missing. This is due to the human intervention in creat-
ing Wikipedia articles. Moreover, the type of the infoboxes in Wikipedia
plays a vital role in the determination of RDF type inference in the
Knowledge Graphs such as DBpedia. Hence, there arouses a necessity to
have the correct infobox type information in the Wikipedia articles. In
this paper, we propose an approach of predicting Wikipedia infobox type
information using both word and network embeddings. Furthermore, the
impact of using minimalistic information such as Table of Contents and Named Entity mentions in the abstract of a Wikipedia article in the prediction process has been analyzed as well.
Keywords:
Wikipedia, Infobox, Embeddings, Knowledge Graph, Classification
%0 Conference Paper
%1 biswas2018wikipedia
%A Biswas, Russa
%A Türker, Rima
%A Bakhshandegan Moghaddam, Farshad
%A Koutraki, Maria
%A Sack, Harald
%D 2018
%K Classification Embeddings Infobox KnowledgeGraph Wikipedia fiziseown
%T Wikipedia Infobox Type Prediction Using Embeddings
%X Wikipedia, the multilingual, free content encyclopedia has
evolved as the largest and the most popular general reference work on the
Internet. Since the time of commencement of Wikipedia, crowd sourcing
of articles has been one of the most salient features of this open encyclo-
pedia. It is obvious that enormous amount of work and expertise goes in
the creation of a self-content article. However, it has been observed that
the infobox type information in Wikipedia articles is often incomplete,
incorrect and missing. This is due to the human intervention in creat-
ing Wikipedia articles. Moreover, the type of the infoboxes in Wikipedia
plays a vital role in the determination of RDF type inference in the
Knowledge Graphs such as DBpedia. Hence, there arouses a necessity to
have the correct infobox type information in the Wikipedia articles. In
this paper, we propose an approach of predicting Wikipedia infobox type
information using both word and network embeddings. Furthermore, the
impact of using minimalistic information such as Table of Contents and Named Entity mentions in the abstract of a Wikipedia article in the prediction process has been analyzed as well.
Keywords:
Wikipedia, Infobox, Embeddings, Knowledge Graph, Classification
@inproceedings{biswas2018wikipedia,
abstract = {Wikipedia, the multilingual, free content encyclopedia has
evolved as the largest and the most popular general reference work on the
Internet. Since the time of commencement of Wikipedia, crowd sourcing
of articles has been one of the most salient features of this open encyclo-
pedia. It is obvious that enormous amount of work and expertise goes in
the creation of a self-content article. However, it has been observed that
the infobox type information in Wikipedia articles is often incomplete,
incorrect and missing. This is due to the human intervention in creat-
ing Wikipedia articles. Moreover, the type of the infoboxes in Wikipedia
plays a vital role in the determination of RDF type inference in the
Knowledge Graphs such as DBpedia. Hence, there arouses a necessity to
have the correct infobox type information in the Wikipedia articles. In
this paper, we propose an approach of predicting Wikipedia infobox type
information using both word and network embeddings. Furthermore, the
impact of using minimalistic information such as Table of Contents and Named Entity mentions in the abstract of a Wikipedia article in the prediction process has been analyzed as well.
Keywords:
Wikipedia, Infobox, Embeddings, Knowledge Graph, Classification},
added-at = {2018-05-25T13:22:20.000+0200},
author = {Biswas, Russa and Türker, Rima and Bakhshandegan Moghaddam, Farshad and Koutraki, Maria and Sack, Harald},
biburl = {https://www.bibsonomy.org/bibtex/2923f2364577f2c5079c36b0659233945/vivienvetter},
eventdate = {2018},
eventtitle = {1st Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies DL4KGS 2018},
interhash = {22a547aa7c58342a22050893d8397431},
intrahash = {923f2364577f2c5079c36b0659233945},
keywords = {Classification Embeddings Infobox KnowledgeGraph Wikipedia fiziseown},
timestamp = {2018-05-25T13:22:20.000+0200},
title = {Wikipedia Infobox Type Prediction Using Embeddings},
venue = {ESWC 2018},
year = 2018
}