Extract Reliable Relations from Wikipedia Texts for Practical Ontology Construction



Título del documento: Extract Reliable Relations from Wikipedia Texts for Practical Ontology Construction
Revista: Computación y sistemas
Base de datos: PERIÓDICA
Número de sistema: 000411065
ISSN: 1405-5546
Autors: 1
2
3
1
Institucions: 1Electronics and Telecommunications Research Institute, Automatic Speech Translation and Language Intelligence Research Department, Daejeon. Corea del Sur
2Chonbuk National University, Division of Computer Science and Engineering, Jeonju. Corea del Sur
3Korea Advanced Institute of Science and Technology, School of Computing, Daejeon. Corea del Sur
Any:
Període: Jul-Sep
Volum: 20
Número: 3
Paginació: 467-476
País: México
Idioma: Inglés
Tipo de documento: Artículo
Enfoque: Experimental, aplicado
Resumen en inglés A feature based relation classification approach is presented in this paper. We aimed to exact relation candidates from Wikipedia texts. A probabilistic and a semantic relatedness features are employed with other linguistic information for the purpose. The experiments show that, relation classification using the proposed relatedness features with surface information like word and part-of-speech tags is competitive with or even outperforms the one of using deep syntactic information. Meanwhile, an approach is proposed to distinguish reliable relation candidates from others, so that these reliable results can be accepted for knowledge building without human verification. The experiments show that, with the relation classification approach presented in this paper, more than 40% of the classification results are reliable, which means, at least 40% of the human and time costs can be saved in practice
Disciplines Ciencias de la computación,
Literatura y lingüística
Paraules clau: Procesamiento de datos,
Lingüística aplicada,
Lingüística computacional,
Análisis de textos,
Extracción de información,
Ontología
Keyword: Computer science,
Literature and linguistics,
Data processing,
Applied linguistics,
Computing linguistics,
Text analysis,
Information extraction,
Ontology
Text complet: Texto completo (Ver HTML)