@inproceedings{rosenthal-etal-2010-towards,
title = "Towards Semi-Automated Annotation for Prepositional Phrase Attachment",
author = "Rosenthal, Sara and
Lipovsky, William and
McKeown, Kathleen and
Thadani, Kapil and
Andreas, Jacob",
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/828_Paper.pdf",
abstract = "This paper investigates whether high-quality annotations for tasks involving semantic disambiguation can be obtained without a major investment in time or expense. We examine the use of untrained human volunteers from Amazons Mechanical Turk in disambiguating prepositional phrase (PP) attachment over sentences drawn from the Wall Street Journal corpus. Our goal is to compare the performance of these crowdsourced judgments to the annotations supplied by trained linguists for the Penn Treebank project in order to indicate the viability of this approach for annotation projects that involve contextual disambiguation. The results of our experiments on a sample of the Wall Street Journal corpus show that invoking majority agreement between multiple human workers can yield PP attachments with fairly high precision. This confirms that a crowdsourcing approach to syntactic annotation holds promise for the generation of training corpora in new domains and genres where high-quality annotations are not available and difficult to obtain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosenthal-etal-2010-towards">
<titleInfo>
<title>Towards Semi-Automated Annotation for Prepositional Phrase Attachment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lipovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kapil</namePart>
<namePart type="family">Thadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</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>This paper investigates whether high-quality annotations for tasks involving semantic disambiguation can be obtained without a major investment in time or expense. We examine the use of untrained human volunteers from Amazons Mechanical Turk in disambiguating prepositional phrase (PP) attachment over sentences drawn from the Wall Street Journal corpus. Our goal is to compare the performance of these crowdsourced judgments to the annotations supplied by trained linguists for the Penn Treebank project in order to indicate the viability of this approach for annotation projects that involve contextual disambiguation. The results of our experiments on a sample of the Wall Street Journal corpus show that invoking majority agreement between multiple human workers can yield PP attachments with fairly high precision. This confirms that a crowdsourcing approach to syntactic annotation holds promise for the generation of training corpora in new domains and genres where high-quality annotations are not available and difficult to obtain.</abstract>
<identifier type="citekey">rosenthal-etal-2010-towards</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/828_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Semi-Automated Annotation for Prepositional Phrase Attachment
%A Rosenthal, Sara
%A Lipovsky, William
%A McKeown, Kathleen
%A Thadani, Kapil
%A Andreas, Jacob
%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 rosenthal-etal-2010-towards
%X This paper investigates whether high-quality annotations for tasks involving semantic disambiguation can be obtained without a major investment in time or expense. We examine the use of untrained human volunteers from Amazons Mechanical Turk in disambiguating prepositional phrase (PP) attachment over sentences drawn from the Wall Street Journal corpus. Our goal is to compare the performance of these crowdsourced judgments to the annotations supplied by trained linguists for the Penn Treebank project in order to indicate the viability of this approach for annotation projects that involve contextual disambiguation. The results of our experiments on a sample of the Wall Street Journal corpus show that invoking majority agreement between multiple human workers can yield PP attachments with fairly high precision. This confirms that a crowdsourcing approach to syntactic annotation holds promise for the generation of training corpora in new domains and genres where high-quality annotations are not available and difficult to obtain.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/828_Paper.pdf
Markdown (Informal)
[Towards Semi-Automated Annotation for Prepositional Phrase Attachment](http://www.lrec-conf.org/proceedings/lrec2010/pdf/828_Paper.pdf) (Rosenthal et al., LREC 2010)
ACL