@inproceedings{rehm-etal-2008-towards,
title = "Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems",
author = {Rehm, Georg and
Santini, Marina and
Mehler, Alexander and
Braslavski, Pavel and
Gleim, R{\"u}diger and
Stubbe, Andrea and
Symonenko, Svetlana and
Tavosanis, Mirko and
Vidulin, Vedrana},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/94_paper.pdf",
abstract = "We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rehm-etal-2008-towards">
<titleInfo>
<title>Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marina</namePart>
<namePart type="family">Santini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Mehler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Braslavski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rüdiger</namePart>
<namePart type="family">Gleim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Stubbe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetlana</namePart>
<namePart type="family">Symonenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirko</namePart>
<namePart type="family">Tavosanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vedrana</namePart>
<namePart type="family">Vidulin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres.</abstract>
<identifier type="citekey">rehm-etal-2008-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/94_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems
%A Rehm, Georg
%A Santini, Marina
%A Mehler, Alexander
%A Braslavski, Pavel
%A Gleim, Rüdiger
%A Stubbe, Andrea
%A Symonenko, Svetlana
%A Tavosanis, Mirko
%A Vidulin, Vedrana
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F rehm-etal-2008-towards
%X We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/94_paper.pdf
Markdown (Informal)
[Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems](http://www.lrec-conf.org/proceedings/lrec2008/pdf/94_paper.pdf) (Rehm et al., LREC 2008)
ACL
- Georg Rehm, Marina Santini, Alexander Mehler, Pavel Braslavski, Rüdiger Gleim, Andrea Stubbe, Svetlana Symonenko, Mirko Tavosanis, and Vedrana Vidulin. 2008. Towards a Reference Corpus of Web Genres for the Evaluation of Genre Identification Systems. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).