@inproceedings{hamon-mostefa-2008-experimental,
title = "An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation",
author = "Hamon, Olivier and
Mostefa, Djamel",
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/900_paper.pdf",
abstract = "This paper describes the evaluation methodology used to evaluate the TC-STAR speech-to-speech translation (SST) system and the results from the third year of the project. It follows the results presented in Hamon (2007), dealing with the first end-to-end evaluation of the project. In this paper, we try to experiment with the methodology and the protocol during a second end-to-end evaluation, by comparing outputs from the TC-STAR system with interpreters from the European parliament. For this purpose, we test different criteria of evaluation and type of questions within a comprehension test. The results show that interpreters do not translate all the information (as opposed to the automatic system), but the quality of SST is still far from that of human translation. The experimental comprehension test used provides new information to study the quality of automatic systems, but without settling the issue of which protocol is the best. This depends on what the evaluator wants to know about the SST: either to have a subjective end-user evaluation or a more objective one.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamon-mostefa-2008-experimental">
<titleInfo>
<title>An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olivier</namePart>
<namePart type="family">Hamon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamel</namePart>
<namePart type="family">Mostefa</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>This paper describes the evaluation methodology used to evaluate the TC-STAR speech-to-speech translation (SST) system and the results from the third year of the project. It follows the results presented in Hamon (2007), dealing with the first end-to-end evaluation of the project. In this paper, we try to experiment with the methodology and the protocol during a second end-to-end evaluation, by comparing outputs from the TC-STAR system with interpreters from the European parliament. For this purpose, we test different criteria of evaluation and type of questions within a comprehension test. The results show that interpreters do not translate all the information (as opposed to the automatic system), but the quality of SST is still far from that of human translation. The experimental comprehension test used provides new information to study the quality of automatic systems, but without settling the issue of which protocol is the best. This depends on what the evaluator wants to know about the SST: either to have a subjective end-user evaluation or a more objective one.</abstract>
<identifier type="citekey">hamon-mostefa-2008-experimental</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/900_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation
%A Hamon, Olivier
%A Mostefa, Djamel
%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 hamon-mostefa-2008-experimental
%X This paper describes the evaluation methodology used to evaluate the TC-STAR speech-to-speech translation (SST) system and the results from the third year of the project. It follows the results presented in Hamon (2007), dealing with the first end-to-end evaluation of the project. In this paper, we try to experiment with the methodology and the protocol during a second end-to-end evaluation, by comparing outputs from the TC-STAR system with interpreters from the European parliament. For this purpose, we test different criteria of evaluation and type of questions within a comprehension test. The results show that interpreters do not translate all the information (as opposed to the automatic system), but the quality of SST is still far from that of human translation. The experimental comprehension test used provides new information to study the quality of automatic systems, but without settling the issue of which protocol is the best. This depends on what the evaluator wants to know about the SST: either to have a subjective end-user evaluation or a more objective one.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/900_paper.pdf
Markdown (Informal)
[An Experimental Methodology for an End-to-End Evaluation in Speech-to-Speech Translation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/900_paper.pdf) (Hamon & Mostefa, LREC 2008)
ACL