Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information
The narrow-down approach, separately composed of search and classification stages, is an effective way of dealing with large-scale hierarchical text classification. Recent approaches introduce methods of incorporating global, local, and path information extracted from web taxonomies in the classific...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Korea Institute of Science and Technology Information
2017-09-01
|
Series: | Journal of Information Science Theory and Practice |
Subjects: | |
Online Access: | http://society.kisti.re.kr/sv/SV_svpsbs03V.do?method=download&cn1=JAKO201727038079760 |
id |
doaj-e24681531e7b4fc4a99b735418092490 |
---|---|
record_format |
Article |
spelling |
doaj-e24681531e7b4fc4a99b7354180924902020-11-24T21:36:15ZengKorea Institute of Science and Technology InformationJournal of Information Science Theory and Practice2287-90992287-45772017-09-0153314710.1633/JISTaP.2017.5.3.322879099Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path InformationOh, Heung-Seon0Jung, Yuchul1Korea Institute of Science and Technology InformationKumoh National Institute of Technology (KIT)The narrow-down approach, separately composed of search and classification stages, is an effective way of dealing with large-scale hierarchical text classification. Recent approaches introduce methods of incorporating global, local, and path information extracted from web taxonomies in the classification stage. Meanwhile, in the case of utilizing path information, there have been few efforts to address existing limitations and develop more sophisticated methods. In this paper, we propose an expansion method to effectively exploit category path information based on the observation that the existing method is exposed to a term mismatch problem and low discrimination power due to insufficient path information. The key idea of our method is to utilize relevant information not presented on category paths by adding more useful words. We evaluate the effectiveness of our method on state-of-the art narrow-down methods and report the results with in-depth analysis.http://society.kisti.re.kr/sv/SV_svpsbs03V.do?method=download&cn1=JAKO201727038079760Hierarchical text classificationQuery expansionNarrow-down approach |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Oh, Heung-Seon Jung, Yuchul |
spellingShingle |
Oh, Heung-Seon Jung, Yuchul Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information Journal of Information Science Theory and Practice Hierarchical text classification Query expansion Narrow-down approach |
author_facet |
Oh, Heung-Seon Jung, Yuchul |
author_sort |
Oh, Heung-Seon |
title |
Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information |
title_short |
Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information |
title_full |
Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information |
title_fullStr |
Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information |
title_full_unstemmed |
Enhancing the Narrow-down Approach to Large-scale Hierarchical Text Classification with Category Path Information |
title_sort |
enhancing the narrow-down approach to large-scale hierarchical text classification with category path information |
publisher |
Korea Institute of Science and Technology Information |
series |
Journal of Information Science Theory and Practice |
issn |
2287-9099 2287-4577 |
publishDate |
2017-09-01 |
description |
The narrow-down approach, separately composed of search and classification stages, is an effective way of dealing with large-scale hierarchical text classification. Recent approaches introduce methods of incorporating global, local, and path information extracted from web taxonomies in the classification stage. Meanwhile, in the case of utilizing path information, there have been few efforts to address existing limitations and develop more sophisticated methods. In this paper, we propose an expansion method to effectively exploit category path information based on the observation that the existing method is exposed to a term mismatch problem and low discrimination power due to insufficient path information. The key idea of our method is to utilize relevant information not presented on category paths by adding more useful words. We evaluate the effectiveness of our method on state-of-the art narrow-down methods and report the results with in-depth analysis. |
topic |
Hierarchical text classification Query expansion Narrow-down approach |
url |
http://society.kisti.re.kr/sv/SV_svpsbs03V.do?method=download&cn1=JAKO201727038079760 |
work_keys_str_mv |
AT ohheungseon enhancingthenarrowdownapproachtolargescalehierarchicaltextclassificationwithcategorypathinformation AT jungyuchul enhancingthenarrowdownapproachtolargescalehierarchicaltextclassificationwithcategorypathinformation |
_version_ |
1725942244596252672 |