@inproceedings{eskevich-etal-2012-creating,
title = "Creating a Data Collection for Evaluating Rich Speech Retrieval",
author = "Eskevich, Maria and
Jones, Gareth J.F. and
Larson, Martha and
Ordelman, Roeland",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/910_Paper.pdf",
pages = "1736--1743",
abstract = "We describe the development of a test collection for the investigation of speech retrieval beyond identification of relevant content. This collection focuses on satisfying user information needs for queries associated with specific types of speech acts. The collection is based on an archive of the Internet video from Internet video sharing platform (blip.tv), and was provided by the MediaEval benchmarking initiative. A crowdsourcing approach was used to identify segments in the video data which contain speech acts, to create a description of the video containing the act and to generate search queries designed to refind this speech act. We describe and reflect on our experiences with crowdsourcing this test collection using the Amazon Mechanical Turk platform. We highlight the challenges of constructing this dataset, including the selection of the data source, design of the crowdsouring task and the specification of queries and relevant items.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eskevich-etal-2012-creating">
<titleInfo>
<title>Creating a Data Collection for Evaluating Rich Speech Retrieval</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gareth</namePart>
<namePart type="given">J.F.</namePart>
<namePart type="family">Jones</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Larson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roeland</namePart>
<namePart type="family">Ordelman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We describe the development of a test collection for the investigation of speech retrieval beyond identification of relevant content. This collection focuses on satisfying user information needs for queries associated with specific types of speech acts. The collection is based on an archive of the Internet video from Internet video sharing platform (blip.tv), and was provided by the MediaEval benchmarking initiative. A crowdsourcing approach was used to identify segments in the video data which contain speech acts, to create a description of the video containing the act and to generate search queries designed to refind this speech act. We describe and reflect on our experiences with crowdsourcing this test collection using the Amazon Mechanical Turk platform. We highlight the challenges of constructing this dataset, including the selection of the data source, design of the crowdsouring task and the specification of queries and relevant items.</abstract>
<identifier type="citekey">eskevich-etal-2012-creating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/910_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1736</start>
<end>1743</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Data Collection for Evaluating Rich Speech Retrieval
%A Eskevich, Maria
%A Jones, Gareth J.F.
%A Larson, Martha
%A Ordelman, Roeland
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F eskevich-etal-2012-creating
%X We describe the development of a test collection for the investigation of speech retrieval beyond identification of relevant content. This collection focuses on satisfying user information needs for queries associated with specific types of speech acts. The collection is based on an archive of the Internet video from Internet video sharing platform (blip.tv), and was provided by the MediaEval benchmarking initiative. A crowdsourcing approach was used to identify segments in the video data which contain speech acts, to create a description of the video containing the act and to generate search queries designed to refind this speech act. We describe and reflect on our experiences with crowdsourcing this test collection using the Amazon Mechanical Turk platform. We highlight the challenges of constructing this dataset, including the selection of the data source, design of the crowdsouring task and the specification of queries and relevant items.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/910_Paper.pdf
%P 1736-1743
Markdown (Informal)
[Creating a Data Collection for Evaluating Rich Speech Retrieval](http://www.lrec-conf.org/proceedings/lrec2012/pdf/910_Paper.pdf) (Eskevich et al., LREC 2012)
ACL
- Maria Eskevich, Gareth J.F. Jones, Martha Larson, and Roeland Ordelman. 2012. Creating a Data Collection for Evaluating Rich Speech Retrieval. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 1736–1743, Istanbul, Turkey. European Language Resources Association (ELRA).