@inproceedings{tomanek-hahn-2008-approximating,
title = "Approximating Learning Curves for Active-Learning-Driven Annotation",
author = "Tomanek, Katrin and
Hahn, Udo",
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/335_paper.pdf",
abstract = "Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning methods for various NLP tasks. A crucial issue rarely addressed, however, is when to actually stop the annotation process to profit from the savings in efforts. This question is tightly related to estimating the classifier performance after a certain amount of data has already been annotated. While learning curves are the default means to monitor the progress of the annotation process in terms of classifier performance, this requires a labeled gold standard which - in realistic annotation settings, at least - is often unavailable. We here propose a method for committee-based AL to approximate the progression of the learning curve based on the disagreement among the committee members. This method relies on a separate, unlabeled corpus and is thus well suited for situations where a labeled gold standard is not available or would be too expensive to obtain. Considering named entity recognition as a test case we provide empirical evidence that this approach works well under simulation as well as under real-world annotation conditions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tomanek-hahn-2008-approximating">
<titleInfo>
<title>Approximating Learning Curves for Active-Learning-Driven Annotation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Tomanek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</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>Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning methods for various NLP tasks. A crucial issue rarely addressed, however, is when to actually stop the annotation process to profit from the savings in efforts. This question is tightly related to estimating the classifier performance after a certain amount of data has already been annotated. While learning curves are the default means to monitor the progress of the annotation process in terms of classifier performance, this requires a labeled gold standard which - in realistic annotation settings, at least - is often unavailable. We here propose a method for committee-based AL to approximate the progression of the learning curve based on the disagreement among the committee members. This method relies on a separate, unlabeled corpus and is thus well suited for situations where a labeled gold standard is not available or would be too expensive to obtain. Considering named entity recognition as a test case we provide empirical evidence that this approach works well under simulation as well as under real-world annotation conditions.</abstract>
<identifier type="citekey">tomanek-hahn-2008-approximating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/335_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Approximating Learning Curves for Active-Learning-Driven Annotation
%A Tomanek, Katrin
%A Hahn, Udo
%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 tomanek-hahn-2008-approximating
%X Active learning (AL) is getting more and more popular as a methodology to considerably reduce the annotation effort when building training material for statistical learning methods for various NLP tasks. A crucial issue rarely addressed, however, is when to actually stop the annotation process to profit from the savings in efforts. This question is tightly related to estimating the classifier performance after a certain amount of data has already been annotated. While learning curves are the default means to monitor the progress of the annotation process in terms of classifier performance, this requires a labeled gold standard which - in realistic annotation settings, at least - is often unavailable. We here propose a method for committee-based AL to approximate the progression of the learning curve based on the disagreement among the committee members. This method relies on a separate, unlabeled corpus and is thus well suited for situations where a labeled gold standard is not available or would be too expensive to obtain. Considering named entity recognition as a test case we provide empirical evidence that this approach works well under simulation as well as under real-world annotation conditions.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/335_paper.pdf
Markdown (Informal)
[Approximating Learning Curves for Active-Learning-Driven Annotation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/335_paper.pdf) (Tomanek & Hahn, LREC 2008)
ACL