@inproceedings{0c8e48ffb2ff4ce29cde5c796361b63b,
title = "Enhanced document clustering using wikipedia-based document representation",
abstract = "Most traditional clustering methods are based on the Vector Space Model (VSM) using {\textquoteleft}Bag of Words{\textquoteright} (BOW) representation. However, the BOW representation which only accounts for term frequency is quite limited because it ignores semantic relations among indexed terms. To resolve this problem, this paper proposes a new method of constructing the matrices of document representation by utilizing the Wikipedia encyclopedia, with not depending on traditional VSM, to significantly enhance the quality of document clustering. Through extensive experiments with popular 20 Newsgroup dataset, we show that our proposed method notably improves clustering performance compared with the traditional VSM-based clustering method.",
author = "Hong, {Ki Joo} and Lee, {Ga Hui} and Kim, {Han Joon}",
note = "Publisher Copyright: {\textcopyright} 2016 Taylor & Francis Group.; International Conference on Applied System Innovation, ICASI 2015 ; Conference date: 22-05-2015 Through 27-05-2015",
year = "2016",
doi = "10.1201/b21811-41",
language = "English",
isbn = "9781138028937",
series = "Applied System Innovation - Proceedings of the International Conference on Applied System Innovation, ICASI 2015",
publisher = "CRC Press/Balkema",
pages = "183--186",
editor = "Teen-Hang Meen and Prior, {Stephen D.} and Lam, {Artde Donald Kin-Tak}",
booktitle = "Applied System Innovation - Proceedings of the International Conference on Applied System Innovation, ICASI 2015",
}