M. Sanderson, and B. Croft. SIGIR '99: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, page 206--213. New York, NY, USA, ACM Press, (1999)
DOI: http://dx.doi.org/10.1145/312624.312679
Abstract
This paper presents a means of automatically deriving a
hierarchical organization of concepts from a set of documents
without use of training data or standard clustering techniques.
Instead, salient words and phrases extracted from the documents
are organized hierarchically using a type of co-occurrence known
as subsumption. The resulting structure is displayed as a series of
hierarchical menus. When generated from a set of retrieved
documents, a user browsing the menus is provided with a detailed
overview of their content in a manner distinct from existing
overview and summarization techniques. The methods used to
build the structure are simple, but appear to be effective: a smallscale
user study reveals that the generated hierarchy possesses
properties expected of such a structure in that general terms are
placed at the top levels leading to related and more specific terms
below. The formation and presentation of the hierarchy is
described along with the user study and some other informal
evaluations.
%0 Conference Paper
%1 sanderson1999
%A Sanderson, Mark
%A Croft, Bruce
%B SIGIR '99: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval
%C New York, NY, USA
%D 1999
%I ACM Press
%K imported
%P 206--213
%R http://dx.doi.org/10.1145/312624.312679
%T Deriving concept hierarchies from text
%U http://dx.doi.org/10.1145/312624.312679
%X This paper presents a means of automatically deriving a
hierarchical organization of concepts from a set of documents
without use of training data or standard clustering techniques.
Instead, salient words and phrases extracted from the documents
are organized hierarchically using a type of co-occurrence known
as subsumption. The resulting structure is displayed as a series of
hierarchical menus. When generated from a set of retrieved
documents, a user browsing the menus is provided with a detailed
overview of their content in a manner distinct from existing
overview and summarization techniques. The methods used to
build the structure are simple, but appear to be effective: a smallscale
user study reveals that the generated hierarchy possesses
properties expected of such a structure in that general terms are
placed at the top levels leading to related and more specific terms
below. The formation and presentation of the hierarchy is
described along with the user study and some other informal
evaluations.
%@ 1581130961
@inproceedings{sanderson1999,
abstract = {This paper presents a means of automatically deriving a
hierarchical organization of concepts from a set of documents
without use of training data or standard clustering techniques.
Instead, salient words and phrases extracted from the documents
are organized hierarchically using a type of co-occurrence known
as subsumption. The resulting structure is displayed as a series of
hierarchical menus. When generated from a set of retrieved
documents, a user browsing the menus is provided with a detailed
overview of their content in a manner distinct from existing
overview and summarization techniques. The methods used to
build the structure are simple, but appear to be effective: a smallscale
user study reveals that the generated hierarchy possesses
properties expected of such a structure in that general terms are
placed at the top levels leading to related and more specific terms
below. The formation and presentation of the hierarchy is
described along with the user study and some other informal
evaluations.},
added-at = {2009-10-23T10:49:34.000+0200},
address = {New York, NY, USA},
at = {2007-02-19 09:35:06},
author = {Sanderson, Mark and Croft, Bruce},
biburl = {https://www.bibsonomy.org/bibtex/2ae161596ec8a89a0455d2683ab2eecfe/gerhard.wohlgenannt},
booktitle = {SIGIR '99: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval},
description = {phd thesis version 2009-10-23},
doi = {http://dx.doi.org/10.1145/312624.312679},
id = {564012},
interhash = {5d9a650a3931879dd330e3c532ba6a4a},
intrahash = {ae161596ec8a89a0455d2683ab2eecfe},
isbn = {1581130961},
keywords = {imported},
pages = {206--213},
priority = {4},
publisher = {ACM Press},
timestamp = {2009-10-23T10:49:39.000+0200},
title = {Deriving concept hierarchies from text},
url = {http://dx.doi.org/10.1145/312624.312679},
year = 1999
}