Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Entity extraction: From unstructured text to DBpedia RDF triples

Exner, Peter LU and Nugues, Pierre LU orcid (2012) The Web of Linked Entities Workshop (WoLE 2012) p.58-69
Abstract
In this paper, we describe an end-to-end system that automatically extracts RDF triples describing entity relations and properties from unstructured text. This system is based on a pipeline of text processing modules that includes a semantic parser and a coreference solver. By using coreference chains, we group entity actions and properties described in different sentences and convert them

into entity triples. We applied our system to over 114,000 Wikipedia articles and we could extract more than 1,000,000 triples. Using an ontology-mapping system that we bootstrapped using existing DBpedia triples, we mapped 189,000 extracted triples onto the DBpedia namespace. These extracted entities are availableonline in the N-Triple format.... (More)
In this paper, we describe an end-to-end system that automatically extracts RDF triples describing entity relations and properties from unstructured text. This system is based on a pipeline of text processing modules that includes a semantic parser and a coreference solver. By using coreference chains, we group entity actions and properties described in different sentences and convert them

into entity triples. We applied our system to over 114,000 Wikipedia articles and we could extract more than 1,000,000 triples. Using an ontology-mapping system that we bootstrapped using existing DBpedia triples, we mapped 189,000 extracted triples onto the DBpedia namespace. These extracted entities are availableonline in the N-Triple format. 1



1 http://semantica.cs.lth.se/ (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
host publication
Proceedings of the Web of Linked Entities Workshop in conjuction with the 11th International Semantic Web Conference (ISWC 2012)
pages
58 - 69
publisher
CEUR-WS
conference name
The Web of Linked Entities Workshop (WoLE 2012)
conference location
Boston, United States
conference dates
2012-11-11
external identifiers
  • scopus:84889575071
ISSN
1613-0073
language
English
LU publication?
yes
id
636681f3-82d6-46f2-bd70-76114b130c1a (old id 3191701)
alternative location
http://ceur-ws.org/Vol-906/paper7.pdf
date added to LUP
2016-04-01 12:55:55
date last changed
2022-03-29 04:32:47
@inproceedings{636681f3-82d6-46f2-bd70-76114b130c1a,
  abstract     = {{In this paper, we describe an end-to-end system that automatically extracts RDF triples describing entity relations and properties from unstructured text. This system is based on a pipeline of text processing modules that includes a semantic parser and a coreference solver. By using coreference chains, we group entity actions and properties described in different sentences and convert them<br/><br>
into entity triples. We applied our system to over 114,000 Wikipedia articles and we could extract more than 1,000,000 triples. Using an ontology-mapping system that we bootstrapped using existing DBpedia triples, we mapped 189,000 extracted triples onto the DBpedia namespace. These extracted entities are availableonline in the N-Triple format. 1<br/><br>
<br/><br>
1 http://semantica.cs.lth.se/}},
  author       = {{Exner, Peter and Nugues, Pierre}},
  booktitle    = {{Proceedings of the Web of Linked Entities Workshop in conjuction with the 11th International Semantic Web Conference (ISWC 2012)}},
  issn         = {{1613-0073}},
  language     = {{eng}},
  pages        = {{58--69}},
  publisher    = {{CEUR-WS}},
  title        = {{Entity extraction: From unstructured text to DBpedia RDF triples}},
  url          = {{https://lup.lub.lu.se/search/files/3053000/3191702.pdf}},
  year         = {{2012}},
}