@inproceedings{cardie-etal-2008-erulemaking,
title = "An e{R}ulemaking Corpus: Identifying Substantive Issues in Public Comments",
author = "Cardie, Claire and
Farina, Cynthia and
Rawding, Matt and
Aijaz, Adil",
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/699_paper.pdf",
abstract = "We describe the creation of a corpus that supports a real-world hierarchical text categorization task in the domain of electronic rulemaking (eRulemaking). Features of the task and of the eRulemaking domain engender both a non-traditional text categorization corpus and a correspondingly difficult machine learning task. Interannotator agreement results are presented for a group of six annotators. We also briefly describe the results of experiments that apply standard and hierarchical text categorization techniques to the eRulemaking data sets. The corpus is the first in a series of related sentence-level text categorization corpora to be developed in the eRulemaking domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cardie-etal-2008-erulemaking">
<titleInfo>
<title>An eRulemaking Corpus: Identifying Substantive Issues in Public Comments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Cardie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cynthia</namePart>
<namePart type="family">Farina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Rawding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adil</namePart>
<namePart type="family">Aijaz</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 describe the creation of a corpus that supports a real-world hierarchical text categorization task in the domain of electronic rulemaking (eRulemaking). Features of the task and of the eRulemaking domain engender both a non-traditional text categorization corpus and a correspondingly difficult machine learning task. Interannotator agreement results are presented for a group of six annotators. We also briefly describe the results of experiments that apply standard and hierarchical text categorization techniques to the eRulemaking data sets. The corpus is the first in a series of related sentence-level text categorization corpora to be developed in the eRulemaking domain.</abstract>
<identifier type="citekey">cardie-etal-2008-erulemaking</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/699_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An eRulemaking Corpus: Identifying Substantive Issues in Public Comments
%A Cardie, Claire
%A Farina, Cynthia
%A Rawding, Matt
%A Aijaz, Adil
%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 cardie-etal-2008-erulemaking
%X We describe the creation of a corpus that supports a real-world hierarchical text categorization task in the domain of electronic rulemaking (eRulemaking). Features of the task and of the eRulemaking domain engender both a non-traditional text categorization corpus and a correspondingly difficult machine learning task. Interannotator agreement results are presented for a group of six annotators. We also briefly describe the results of experiments that apply standard and hierarchical text categorization techniques to the eRulemaking data sets. The corpus is the first in a series of related sentence-level text categorization corpora to be developed in the eRulemaking domain.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/699_paper.pdf
Markdown (Informal)
[An eRulemaking Corpus: Identifying Substantive Issues in Public Comments](http://www.lrec-conf.org/proceedings/lrec2008/pdf/699_paper.pdf) (Cardie et al., LREC 2008)
ACL