A method for automatically extracting domain semantic networks from wikipedia

Authors:
Clarissa Castellã Xavier;Vera Lúcia Strube de Lima
Affiliations:
PPGCC --- PUCRS, Porto Alegre, Brazil;PPGCC --- PUCRS, Porto Alegre, Brazil
Venue:
PROPOR'12 Proceedings of the 10th international conference on Computational Processing of the Portuguese Language
Year:
2012

Citing 7
Cited 0

YAGO: A Large Ontology from Wikipedia and WordNet

Web Semantics: Science, Services and Agents on the World Wide Web
DBpedia: a nucleus for a web of open data

ISWC'07/ASWC'07 Proceedings of the 6th international The semantic web and 2nd Asian conference on Asian semantic web conference
BabelNet: building a very large multilingual semantic network

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Unsupervised techniques for discovering ontology elements from Wikipedia article links

FAM-LbR '10 Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading
Automatically acquiring a semantic network of related concepts

CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
MENTA: inducing multilingual taxonomies from wikipedia

CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
A semi-automatic method for domain ontology extraction from Portuguese language Wikipedia's categories

SBIA'10 Proceedings of the 20th Brazilian conference on Advances in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a method for automatically extracting domain semantic networks of concepts connected by non-specific relations from Wikipedia. We propose an approach based on category and link structure analysis. The method consists of two main tasks: concepts extraction and relations acquisition. For each task we developed two different implementation strategies. Aiming to identify what strategies have the best performances we conducted different extractions for two domains and we analyze their results. From this evaluation we discuss the best approach to implement the extraction method.