@inproceedings{b4c6138daa5343f182768ff465772184,
title = "Named entity corpus construction using Wikipedia and DBpedia ontology",
abstract = "In this paper, we propose a novel method to automatically build a named entity corpus based on the DBpedia ontology. Since most of named entity recognition systems require time and effort consuming annotation tasks as training data. Work on NER has thus for been limited on certain languages like English that are resource-abundant in general. As an alternative, we suggest that the NE corpus generated by our proposed method, can be used as training data. Our approach introduces Wikipedia as a raw text and uses the DBpedia data set for named entity disambiguation. Our method is language-independent and easy to be applied to many different languages where Wikipedia and DBpedia are provided. Throughout the paper, we demonstrate that our NE corpus is of comparable quality even to the manually annotated NE corpus.",
keywords = "Corpus, Linked data, Named entity recognition",
author = "Younggyun Hahm and Jungyeul Park and Kyungtae Lim and Youngsik Kim and Dosam Hwang and Choi, \{Key Sun\}",
year = "2014",
language = "English",
series = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
publisher = "European Language Resources Association (ELRA)",
pages = "2565--2569",
editor = "Nicoletta Calzolari and Khalid Choukri and Sara Goggi and Thierry Declerck and Joseph Mariani and Bente Maegaard and Asuncion Moreno and Jan Odijk and Helene Mazo and Stelios Piperidis and Hrafn Loftsson",
booktitle = "Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC 2014",
note = "9th International Conference on Language Resources and Evaluation, LREC 2014 ; Conference date: 26-05-2014 Through 31-05-2014",
}