@inproceedings{bentivogli-etal-2021-cascade,
title = "Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?",
author = "Bentivogli, Luisa and
Cettolo, Mauro and
Gaido, Marco and
Karakanta, Alina and
Martinelli, Alberto and
Negri, Matteo and
Turchi, Marco",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.224",
doi = "10.18653/v1/2021.acl-long.224",
pages = "2873--2887",
abstract = "Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the two is closed? Starting from this question, we present a systematic comparison between state-of-the-art systems representative of the two paradigms. Focusing on three language directions (English-German/Italian/Spanish), we conduct automatic and manual evaluations, exploiting high-quality professional post-edits and annotations. Our multi-faceted analysis on one of the few publicly available ST benchmarks attests for the first time that: i) the gap between the two paradigms is now closed, and ii) the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bentivogli-etal-2021-cascade">
<titleInfo>
<title>Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Martinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</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 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the two is closed? Starting from this question, we present a systematic comparison between state-of-the-art systems representative of the two paradigms. Focusing on three language directions (English-German/Italian/Spanish), we conduct automatic and manual evaluations, exploiting high-quality professional post-edits and annotations. Our multi-faceted analysis on one of the few publicly available ST benchmarks attests for the first time that: i) the gap between the two paradigms is now closed, and ii) the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.</abstract>
<identifier type="citekey">bentivogli-etal-2021-cascade</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.224</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.224</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2873</start>
<end>2887</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?
%A Bentivogli, Luisa
%A Cettolo, Mauro
%A Gaido, Marco
%A Karakanta, Alina
%A Martinelli, Alberto
%A Negri, Matteo
%A Turchi, Marco
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F bentivogli-etal-2021-cascade
%X Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the two is closed? Starting from this question, we present a systematic comparison between state-of-the-art systems representative of the two paradigms. Focusing on three language directions (English-German/Italian/Spanish), we conduct automatic and manual evaluations, exploiting high-quality professional post-edits and annotations. Our multi-faceted analysis on one of the few publicly available ST benchmarks attests for the first time that: i) the gap between the two paradigms is now closed, and ii) the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.
%R 10.18653/v1/2021.acl-long.224
%U https://aclanthology.org/2021.acl-long.224
%U https://doi.org/10.18653/v1/2021.acl-long.224
%P 2873-2887
Markdown (Informal)
[Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?](https://aclanthology.org/2021.acl-long.224) (Bentivogli et al., ACL-IJCNLP 2021)
ACL
- Luisa Bentivogli, Mauro Cettolo, Marco Gaido, Alina Karakanta, Alberto Martinelli, Matteo Negri, and Marco Turchi. 2021. Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2873–2887, Online. Association for Computational Linguistics.