@inproceedings{de-groc-tannier-2014-evaluating,
title = "Evaluating Web-as-corpus Topical Document Retrieval with an Index of the {O}pen{D}irectory",
author = "de Groc, Cl{\'e}ment and
Tannier, Xavier",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/980_Paper.pdf",
abstract = "This article introduces a novel protocol and resource to evaluate Web-as-corpus topical document retrieval. To the contrary of previous work, our goal is to provide an automatic, reproducible and robust evaluation for this task. We rely on the OpenDirectory (DMOZ) as a source of topically annotated webpages and index them in a search engine. With this OpenDirectory search engine, we can then easily evaluate the impact of various parameters such as the number of seed terms, queries or documents, or the usefulness of various term selection algorithms. A first fully automatic evaluation is described and provides baseline performances for this task. The article concludes with practical information regarding the availability of the index and resource files.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-groc-tannier-2014-evaluating">
<titleInfo>
<title>Evaluating Web-as-corpus Topical Document Retrieval with an Index of the OpenDirectory</title>
</titleInfo>
<name type="personal">
<namePart type="given">Clément</namePart>
<namePart type="family">de Groc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Tannier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article introduces a novel protocol and resource to evaluate Web-as-corpus topical document retrieval. To the contrary of previous work, our goal is to provide an automatic, reproducible and robust evaluation for this task. We rely on the OpenDirectory (DMOZ) as a source of topically annotated webpages and index them in a search engine. With this OpenDirectory search engine, we can then easily evaluate the impact of various parameters such as the number of seed terms, queries or documents, or the usefulness of various term selection algorithms. A first fully automatic evaluation is described and provides baseline performances for this task. The article concludes with practical information regarding the availability of the index and resource files.</abstract>
<identifier type="citekey">de-groc-tannier-2014-evaluating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/980_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Web-as-corpus Topical Document Retrieval with an Index of the OpenDirectory
%A de Groc, Clément
%A Tannier, Xavier
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F de-groc-tannier-2014-evaluating
%X This article introduces a novel protocol and resource to evaluate Web-as-corpus topical document retrieval. To the contrary of previous work, our goal is to provide an automatic, reproducible and robust evaluation for this task. We rely on the OpenDirectory (DMOZ) as a source of topically annotated webpages and index them in a search engine. With this OpenDirectory search engine, we can then easily evaluate the impact of various parameters such as the number of seed terms, queries or documents, or the usefulness of various term selection algorithms. A first fully automatic evaluation is described and provides baseline performances for this task. The article concludes with practical information regarding the availability of the index and resource files.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/980_Paper.pdf
Markdown (Informal)
[Evaluating Web-as-corpus Topical Document Retrieval with an Index of the OpenDirectory](http://www.lrec-conf.org/proceedings/lrec2014/pdf/980_Paper.pdf) (de Groc & Tannier, LREC 2014)
ACL