@inproceedings{cd30c051cea5481b990fb9d91fa26a15,

title = "Semantically enriching text representation model for document clustering",

abstract = "This paper presents a novel text space model that represents textual documents for document clustering, which contains the 'concept' space independently of the 'document' and 'term' spaces. The text model described here represents documents as matrices (i.e., 2nd-order tensors), and a document corpus is represented as a 3rd-order tensor. For this, it is necessary to produce the concept vector for each term that occurs in a given document, which is related to word sense disambiguation. As an external knowledge source for concept weighting, we employ the Wikipedia encyclopedia.",

keywords = "Concepts, Document clustering, Tensor space model, Text mining, Vector space model, Wikipedia",

author = "Kim, {Han Joon} and Hong, {Kee Joo} and Chang, {Jae Young}",

note = "Publisher Copyright: Copyright 2015 ACM.; 30th Annual ACM Symposium on Applied Computing, SAC 2015 ; Conference date: 13-04-2015 Through 17-04-2015",

year = "2015",

month = apr,

day = "13",

doi = "10.1145/2695664.2696055",

language = "English",

series = "Proceedings of the ACM Symposium on Applied Computing",

publisher = "Association for Computing Machinery",

pages = "922--925",

editor = "Dongwan Shin",

booktitle = "2015 Symposium on Applied Computing, SAC 2015",

}