@inproceedings{sharoff-etal-2010-web,
title = "The Web Library of Babel: evaluating genre collections",
author = "Sharoff, Serge and
Wu, Zhili and
Markert, Katja",
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/28_Paper.pdf",
abstract = "We present experiments in automatic genre classification on web corpora, comparing a wide variety of features on several different genreannotated datasets (HGC, I-EN, KI-04, KRYS-I, MGC and SANTINIS).We investigate the performance of several types of features (POS n-grams, character n-grams and word n-grams) and show that simple character n-grams perform best on current collections because of their ability to generalise both lexical and syntactic phenomena related to genres. However, we also show that these impressive results might not be transferrable to the wider web due to the lack of comparability between different annotation labels (many webpages cannot be described in terms of the genre labels in individual collections), lack of representativeness of existing collections (many genres are represented by webpages coming from a small number of sources) as well as problems in the reliability of genre annotation (many pages from the web are difficult to interpret in terms of the labels available). This suggests that more research is needed to understand genres on the Web.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharoff-etal-2010-web">
<titleInfo>
<title>The Web Library of Babel: evaluating genre collections</title>
</titleInfo>
<name type="personal">
<namePart type="given">Serge</namePart>
<namePart type="family">Sharoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhili</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katja</namePart>
<namePart type="family">Markert</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>We present experiments in automatic genre classification on web corpora, comparing a wide variety of features on several different genreannotated datasets (HGC, I-EN, KI-04, KRYS-I, MGC and SANTINIS).We investigate the performance of several types of features (POS n-grams, character n-grams and word n-grams) and show that simple character n-grams perform best on current collections because of their ability to generalise both lexical and syntactic phenomena related to genres. However, we also show that these impressive results might not be transferrable to the wider web due to the lack of comparability between different annotation labels (many webpages cannot be described in terms of the genre labels in individual collections), lack of representativeness of existing collections (many genres are represented by webpages coming from a small number of sources) as well as problems in the reliability of genre annotation (many pages from the web are difficult to interpret in terms of the labels available). This suggests that more research is needed to understand genres on the Web.</abstract>
<identifier type="citekey">sharoff-etal-2010-web</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/28_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Web Library of Babel: evaluating genre collections
%A Sharoff, Serge
%A Wu, Zhili
%A Markert, Katja
%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 sharoff-etal-2010-web
%X We present experiments in automatic genre classification on web corpora, comparing a wide variety of features on several different genreannotated datasets (HGC, I-EN, KI-04, KRYS-I, MGC and SANTINIS).We investigate the performance of several types of features (POS n-grams, character n-grams and word n-grams) and show that simple character n-grams perform best on current collections because of their ability to generalise both lexical and syntactic phenomena related to genres. However, we also show that these impressive results might not be transferrable to the wider web due to the lack of comparability between different annotation labels (many webpages cannot be described in terms of the genre labels in individual collections), lack of representativeness of existing collections (many genres are represented by webpages coming from a small number of sources) as well as problems in the reliability of genre annotation (many pages from the web are difficult to interpret in terms of the labels available). This suggests that more research is needed to understand genres on the Web.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/28_Paper.pdf
Markdown (Informal)
[The Web Library of Babel: evaluating genre collections](http://www.lrec-conf.org/proceedings/lrec2010/pdf/28_Paper.pdf) (Sharoff et al., LREC 2010)
ACL
- Serge Sharoff, Zhili Wu, and Katja Markert. 2010. The Web Library of Babel: evaluating genre collections. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).