@inproceedings{condon-etal-2008-applying,
title = "Applying Automated Metrics to Speech Translation Dialogs",
author = "Condon, Sherri and
Phillips, Jon and
Doran, Christy and
Aberdeen, John and
Parvaz, Dan and
Oshika, Beatrice and
Sanders, Greg and
Schlenoff, Craig",
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/535_paper.pdf",
abstract = "Over the past five years, the Defense Advanced Research Projects Agency (DARPA) has funded development of speech translation systems for tactical applications. A key component of the research program has been extensive system evaluation, with dual objectives of assessing progress overall and comparing among systems. This paper describes the methods used to obtain BLEU, TER, and METEOR scores for two-way English-Iraqi Arabic systems. We compare the scores with measures based on human judgments and demonstrate the effects of normalization operations on BLEU scores. Issues that are highlighted include the quality of test data and differential results of applying automated metrics to Arabic vs. English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="condon-etal-2008-applying">
<titleInfo>
<title>Applying Automated Metrics to Speech Translation Dialogs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sherri</namePart>
<namePart type="family">Condon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jon</namePart>
<namePart type="family">Phillips</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Aberdeen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Parvaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Oshika</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Sanders</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Schlenoff</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>Over the past five years, the Defense Advanced Research Projects Agency (DARPA) has funded development of speech translation systems for tactical applications. A key component of the research program has been extensive system evaluation, with dual objectives of assessing progress overall and comparing among systems. This paper describes the methods used to obtain BLEU, TER, and METEOR scores for two-way English-Iraqi Arabic systems. We compare the scores with measures based on human judgments and demonstrate the effects of normalization operations on BLEU scores. Issues that are highlighted include the quality of test data and differential results of applying automated metrics to Arabic vs. English.</abstract>
<identifier type="citekey">condon-etal-2008-applying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/535_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Applying Automated Metrics to Speech Translation Dialogs
%A Condon, Sherri
%A Phillips, Jon
%A Doran, Christy
%A Aberdeen, John
%A Parvaz, Dan
%A Oshika, Beatrice
%A Sanders, Greg
%A Schlenoff, Craig
%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 condon-etal-2008-applying
%X Over the past five years, the Defense Advanced Research Projects Agency (DARPA) has funded development of speech translation systems for tactical applications. A key component of the research program has been extensive system evaluation, with dual objectives of assessing progress overall and comparing among systems. This paper describes the methods used to obtain BLEU, TER, and METEOR scores for two-way English-Iraqi Arabic systems. We compare the scores with measures based on human judgments and demonstrate the effects of normalization operations on BLEU scores. Issues that are highlighted include the quality of test data and differential results of applying automated metrics to Arabic vs. English.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/535_paper.pdf
Markdown (Informal)
[Applying Automated Metrics to Speech Translation Dialogs](http://www.lrec-conf.org/proceedings/lrec2008/pdf/535_paper.pdf) (Condon et al., LREC 2008)
ACL
- Sherri Condon, Jon Phillips, Christy Doran, John Aberdeen, Dan Parvaz, Beatrice Oshika, Greg Sanders, and Craig Schlenoff. 2008. Applying Automated Metrics to Speech Translation Dialogs. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).