@inproceedings{ringger-etal-2008-assessing,
title = "Assessing the Costs of Machine-Assisted Corpus Annotation through a User Study",
author = "Ringger, Eric and
Carmen, Marc and
Haertel, Robbie and
Seppi, Kevin and
Lonsdale, Deryle and
McClanahan, Peter and
Carroll, James and
Ellison, Noel",
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/832_paper.pdf",
abstract = {Fixed, limited budgets often constrain the amount of expert annotation that can go into the construction of annotated corpora. Estimating the cost of annotation is the first step toward using annotation resources wisely. We present here a study of the cost of annotation. This study includes the participation of annotators at various skill levels and with varying backgrounds. Conducted over the web, the study consists of tests that simulate machine-assisted pre-annotation, requiring correction by the annotator rather than annotation from scratch. The study also includes tests representative of an annotation scenario involving Active Learning as it progresses from a na{\"\i}ve model to a knowledgeable model; in particular, annotators encounter pre-annotation of varying degrees of accuracy. The annotation interface lists tags considered likely by the annotation model in preference to other tags. We present the experimental parameters of the study and report both descriptive and inferential statistics on the results of the study. We conclude with a model for estimating the hourly cost of annotation for annotators of various skill levels. We also present models for two granularities of annotation: sentence at a time and word at a time.},
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ringger-etal-2008-assessing">
<titleInfo>
<title>Assessing the Costs of Machine-Assisted Corpus Annotation through a User Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Ringger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Carmen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robbie</namePart>
<namePart type="family">Haertel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Seppi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deryle</namePart>
<namePart type="family">Lonsdale</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">McClanahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Carroll</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noel</namePart>
<namePart type="family">Ellison</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>Fixed, limited budgets often constrain the amount of expert annotation that can go into the construction of annotated corpora. Estimating the cost of annotation is the first step toward using annotation resources wisely. We present here a study of the cost of annotation. This study includes the participation of annotators at various skill levels and with varying backgrounds. Conducted over the web, the study consists of tests that simulate machine-assisted pre-annotation, requiring correction by the annotator rather than annotation from scratch. The study also includes tests representative of an annotation scenario involving Active Learning as it progresses from a naïve model to a knowledgeable model; in particular, annotators encounter pre-annotation of varying degrees of accuracy. The annotation interface lists tags considered likely by the annotation model in preference to other tags. We present the experimental parameters of the study and report both descriptive and inferential statistics on the results of the study. We conclude with a model for estimating the hourly cost of annotation for annotators of various skill levels. We also present models for two granularities of annotation: sentence at a time and word at a time.</abstract>
<identifier type="citekey">ringger-etal-2008-assessing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/832_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Assessing the Costs of Machine-Assisted Corpus Annotation through a User Study
%A Ringger, Eric
%A Carmen, Marc
%A Haertel, Robbie
%A Seppi, Kevin
%A Lonsdale, Deryle
%A McClanahan, Peter
%A Carroll, James
%A Ellison, Noel
%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 ringger-etal-2008-assessing
%X Fixed, limited budgets often constrain the amount of expert annotation that can go into the construction of annotated corpora. Estimating the cost of annotation is the first step toward using annotation resources wisely. We present here a study of the cost of annotation. This study includes the participation of annotators at various skill levels and with varying backgrounds. Conducted over the web, the study consists of tests that simulate machine-assisted pre-annotation, requiring correction by the annotator rather than annotation from scratch. The study also includes tests representative of an annotation scenario involving Active Learning as it progresses from a naïve model to a knowledgeable model; in particular, annotators encounter pre-annotation of varying degrees of accuracy. The annotation interface lists tags considered likely by the annotation model in preference to other tags. We present the experimental parameters of the study and report both descriptive and inferential statistics on the results of the study. We conclude with a model for estimating the hourly cost of annotation for annotators of various skill levels. We also present models for two granularities of annotation: sentence at a time and word at a time.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/832_paper.pdf
Markdown (Informal)
[Assessing the Costs of Machine-Assisted Corpus Annotation through a User Study](http://www.lrec-conf.org/proceedings/lrec2008/pdf/832_paper.pdf) (Ringger et al., LREC 2008)
ACL