@inproceedings{aggarwal-etal-2012-twins,
title = "The Twins Corpus of Museum Visitor Questions",
author = "Aggarwal, Priti and
Artstein, Ron and
Gerten, Jillian and
Katsamanis, Athanasios and
Narayanan, Shrikanth and
Nazarian, Angela and
Traum, David",
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/595_Paper.pdf",
pages = "2355--2361",
abstract = "The Twins corpus is a collection of utterances spoken in interactions with two virtual characters who serve as guides at the Museum of Science in Boston. The corpus contains about 200,000 spoken utterances from museum visitors (primarily children) as well as from trained handlers who work at the museum. In addition to speech recordings, the corpus contains the outputs of speech recognition performed at the time of utterance as well as the system interpretation of the utterances. Parts of the corpus have been manually transcribed and annotated for question interpretation. The corpus has been used for improving performance of the museum characters and for a variety of research projects, such as phonetic-based Natural Language Understanding, creation of conversational characters from text resources, dialogue policy learning, and research on patterns of user interaction. It has the potential to be used for research on children's speech and on language used when talking to a virtual human.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aggarwal-etal-2012-twins">
<titleInfo>
<title>The Twins Corpus of Museum Visitor Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Priti</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ron</namePart>
<namePart type="family">Artstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jillian</namePart>
<namePart type="family">Gerten</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Athanasios</namePart>
<namePart type="family">Katsamanis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrikanth</namePart>
<namePart type="family">Narayanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Nazarian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</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>The Twins corpus is a collection of utterances spoken in interactions with two virtual characters who serve as guides at the Museum of Science in Boston. The corpus contains about 200,000 spoken utterances from museum visitors (primarily children) as well as from trained handlers who work at the museum. In addition to speech recordings, the corpus contains the outputs of speech recognition performed at the time of utterance as well as the system interpretation of the utterances. Parts of the corpus have been manually transcribed and annotated for question interpretation. The corpus has been used for improving performance of the museum characters and for a variety of research projects, such as phonetic-based Natural Language Understanding, creation of conversational characters from text resources, dialogue policy learning, and research on patterns of user interaction. It has the potential to be used for research on children’s speech and on language used when talking to a virtual human.</abstract>
<identifier type="citekey">aggarwal-etal-2012-twins</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/595_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2355</start>
<end>2361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Twins Corpus of Museum Visitor Questions
%A Aggarwal, Priti
%A Artstein, Ron
%A Gerten, Jillian
%A Katsamanis, Athanasios
%A Narayanan, Shrikanth
%A Nazarian, Angela
%A Traum, David
%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 aggarwal-etal-2012-twins
%X The Twins corpus is a collection of utterances spoken in interactions with two virtual characters who serve as guides at the Museum of Science in Boston. The corpus contains about 200,000 spoken utterances from museum visitors (primarily children) as well as from trained handlers who work at the museum. In addition to speech recordings, the corpus contains the outputs of speech recognition performed at the time of utterance as well as the system interpretation of the utterances. Parts of the corpus have been manually transcribed and annotated for question interpretation. The corpus has been used for improving performance of the museum characters and for a variety of research projects, such as phonetic-based Natural Language Understanding, creation of conversational characters from text resources, dialogue policy learning, and research on patterns of user interaction. It has the potential to be used for research on children’s speech and on language used when talking to a virtual human.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/595_Paper.pdf
%P 2355-2361
Markdown (Informal)
[The Twins Corpus of Museum Visitor Questions](http://www.lrec-conf.org/proceedings/lrec2012/pdf/595_Paper.pdf) (Aggarwal et al., LREC 2012)
ACL
- Priti Aggarwal, Ron Artstein, Jillian Gerten, Athanasios Katsamanis, Shrikanth Narayanan, Angela Nazarian, and David Traum. 2012. The Twins Corpus of Museum Visitor Questions. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2355–2361, Istanbul, Turkey. European Language Resources Association (ELRA).