NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH

Semantic annotation of named entities for enriching unstructured content is a critical step in development of Semantic Web and many Natural Language Processing applications. To this end, this paper addresses the named entity disambiguation problem that aims at detecting entity mentions in a text and...

Full description

Bibliographic Details
Main Authors: HienT. Nguyen, TruH. Cao
Format: Article
Language:English
Published: Springer 2012-11-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://www.atlantis-press.com/article/25868036.pdf
_version_ 1818543391680495616
author HienT. Nguyen
TruH. Cao
author_facet HienT. Nguyen
TruH. Cao
author_sort HienT. Nguyen
collection DOAJ
description Semantic annotation of named entities for enriching unstructured content is a critical step in development of Semantic Web and many Natural Language Processing applications. To this end, this paper addresses the named entity disambiguation problem that aims at detecting entity mentions in a text and then linking them to entries in a knowledge base. In this paper, we propose a hybrid method, combining heuristics and statistics, for named entity disambiguation. The novelty is that the disambiguation process is incremental and includes several rounds that filter the candidate referents, by exploiting previously identified entities and extending the text by those entity attributes every time they are successfully resolved in a round. Experiments are conducted to evaluate and show the advantages of the proposed method. The experiment results show that our approach achieves high accuracy and can be used to construct a robust entity disambiguation system.
first_indexed 2024-12-11T22:34:46Z
format Article
id doaj.art-76cf558c99304fc28868f6dc1ffbf016
institution Directory Open Access Journal
issn 1875-6883
language English
last_indexed 2024-12-11T22:34:46Z
publishDate 2012-11-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj.art-76cf558c99304fc28868f6dc1ffbf0162022-12-22T00:48:01ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832012-11-015610.1080/18756891.2012.747661NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACHHienT. NguyenTruH. CaoSemantic annotation of named entities for enriching unstructured content is a critical step in development of Semantic Web and many Natural Language Processing applications. To this end, this paper addresses the named entity disambiguation problem that aims at detecting entity mentions in a text and then linking them to entries in a knowledge base. In this paper, we propose a hybrid method, combining heuristics and statistics, for named entity disambiguation. The novelty is that the disambiguation process is incremental and includes several rounds that filter the candidate referents, by exploiting previously identified entities and extending the text by those entity attributes every time they are successfully resolved in a round. Experiments are conducted to evaluate and show the advantages of the proposed method. The experiment results show that our approach achieves high accuracy and can be used to construct a robust entity disambiguation system.https://www.atlantis-press.com/article/25868036.pdfEntity disambiguationEntity linkingNamed entityKnowledge baseWikipedia
spellingShingle HienT. Nguyen
TruH. Cao
NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
International Journal of Computational Intelligence Systems
Entity disambiguation
Entity linking
Named entity
Knowledge base
Wikipedia
title NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
title_full NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
title_fullStr NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
title_full_unstemmed NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
title_short NAMED ENTITY DISAMBIGUATION: A HYBRID APPROACH
title_sort named entity disambiguation a hybrid approach
topic Entity disambiguation
Entity linking
Named entity
Knowledge base
Wikipedia
url https://www.atlantis-press.com/article/25868036.pdf
work_keys_str_mv AT hientnguyen namedentitydisambiguationahybridapproach
AT truhcao namedentitydisambiguationahybridapproach