@inproceedings{fantinuoli-prandi-2021-towards,
title = "Towards the evaluation of automatic simultaneous speech translation from a communicative perspective",
author = "Fantinuoli, Claudio and
Prandi, Bianca",
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.29",
doi = "10.18653/v1/2021.iwslt-1.29",
pages = "245--254",
abstract = "In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine by comparing it to the performance of professional simultaneous interpreters. To do so, we adopt a framework developed for the assessment of human interpreters and use it to perform a manual evaluation on both human and machine performances. In our sample, we found better performance for the human interpreters in terms of intelligibility, while the machine performs slightly better in terms of informativeness. The limitations of the study and the possible enhancements of the chosen framework are discussed. Despite its intrinsic limitations, the use of this framework represents a first step towards a user-centric and communication-oriented methodology for evaluating real-time automatic speech translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fantinuoli-prandi-2021-towards">
<titleInfo>
<title>Towards the evaluation of automatic simultaneous speech translation from a communicative perspective</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Fantinuoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bianca</namePart>
<namePart type="family">Prandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stuker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine by comparing it to the performance of professional simultaneous interpreters. To do so, we adopt a framework developed for the assessment of human interpreters and use it to perform a manual evaluation on both human and machine performances. In our sample, we found better performance for the human interpreters in terms of intelligibility, while the machine performs slightly better in terms of informativeness. The limitations of the study and the possible enhancements of the chosen framework are discussed. Despite its intrinsic limitations, the use of this framework represents a first step towards a user-centric and communication-oriented methodology for evaluating real-time automatic speech translation.</abstract>
<identifier type="citekey">fantinuoli-prandi-2021-towards</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.29</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.29</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>245</start>
<end>254</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards the evaluation of automatic simultaneous speech translation from a communicative perspective
%A Fantinuoli, Claudio
%A Prandi, Bianca
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F fantinuoli-prandi-2021-towards
%X In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine by comparing it to the performance of professional simultaneous interpreters. To do so, we adopt a framework developed for the assessment of human interpreters and use it to perform a manual evaluation on both human and machine performances. In our sample, we found better performance for the human interpreters in terms of intelligibility, while the machine performs slightly better in terms of informativeness. The limitations of the study and the possible enhancements of the chosen framework are discussed. Despite its intrinsic limitations, the use of this framework represents a first step towards a user-centric and communication-oriented methodology for evaluating real-time automatic speech translation.
%R 10.18653/v1/2021.iwslt-1.29
%U https://aclanthology.org/2021.iwslt-1.29
%U https://doi.org/10.18653/v1/2021.iwslt-1.29
%P 245-254
Markdown (Informal)
[Towards the evaluation of automatic simultaneous speech translation from a communicative perspective](https://aclanthology.org/2021.iwslt-1.29) (Fantinuoli & Prandi, IWSLT 2021)
ACL