@inproceedings{rosell-2010-text,
title = "Text Cluster Trimming for Better Descriptions and Improved Quality",
author = "Rosell, Magnus",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/540_Paper.pdf",
abstract = "Text clustering is potentially very useful for exploration of text sets that are too large to study manually. The success of such a tool depends on whether the results can be explained to the user. An automatically extracted cluster description usually consists of a few words that are deemed representative for the cluster. It is preferably short in order to be easily grasped. However, text cluster content is often diverse. We introduce a trimming method that removes texts that do not contain any, or a few of the words in the cluster description. The result is clusters that match their descriptions better. In experiments on two quite different text sets we obtain significant improvements in both internal and external clustering quality for the trimmed clustering compared to the original. The trimming thus has two positive effects: it forces the clusters to agree with their descriptions (resulting in better descriptions) and improves the quality of the trimmed clusters.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosell-2010-text">
<titleInfo>
<title>Text Cluster Trimming for Better Descriptions and Improved Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Magnus</namePart>
<namePart type="family">Rosell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text clustering is potentially very useful for exploration of text sets that are too large to study manually. The success of such a tool depends on whether the results can be explained to the user. An automatically extracted cluster description usually consists of a few words that are deemed representative for the cluster. It is preferably short in order to be easily grasped. However, text cluster content is often diverse. We introduce a trimming method that removes texts that do not contain any, or a few of the words in the cluster description. The result is clusters that match their descriptions better. In experiments on two quite different text sets we obtain significant improvements in both internal and external clustering quality for the trimmed clustering compared to the original. The trimming thus has two positive effects: it forces the clusters to agree with their descriptions (resulting in better descriptions) and improves the quality of the trimmed clusters.</abstract>
<identifier type="citekey">rosell-2010-text</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/540_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Cluster Trimming for Better Descriptions and Improved Quality
%A Rosell, Magnus
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F rosell-2010-text
%X Text clustering is potentially very useful for exploration of text sets that are too large to study manually. The success of such a tool depends on whether the results can be explained to the user. An automatically extracted cluster description usually consists of a few words that are deemed representative for the cluster. It is preferably short in order to be easily grasped. However, text cluster content is often diverse. We introduce a trimming method that removes texts that do not contain any, or a few of the words in the cluster description. The result is clusters that match their descriptions better. In experiments on two quite different text sets we obtain significant improvements in both internal and external clustering quality for the trimmed clustering compared to the original. The trimming thus has two positive effects: it forces the clusters to agree with their descriptions (resulting in better descriptions) and improves the quality of the trimmed clusters.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/540_Paper.pdf
Markdown (Informal)
[Text Cluster Trimming for Better Descriptions and Improved Quality](http://www.lrec-conf.org/proceedings/lrec2010/pdf/540_Paper.pdf) (Rosell, LREC 2010)
ACL