@inproceedings{machacek-etal-2023-robustness,
title = "Robustness of Multi-Source {MT} to Transcription Errors",
author = "Mach{\'a}{\v{c}}ek, Dominik and
Pol{\'a}k, Peter and
Bojar, Ond{\v{r}}ej and
Dabre, Raj",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.228",
doi = "10.18653/v1/2023.findings-acl.228",
pages = "3707--3723",
abstract = "Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling. In this paper, we hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain. To this end, we first show that on a 10-hour ESIC corpus, the ASR errors in the original English speech and its simultaneous interpreting into German and Czech are mutually independent. We then use two sources, English and German, in a multi-source setting for translation into Czech to establish its robustness to ASR errors. Furthermore, we observe this robustness when translating both noisy sources together in a simultaneous translation setting. Our results show that multi-source neural machine translation has the potential to be useful in a real-time simultaneous translation setting, thereby motivating further investigation in this area.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="machacek-etal-2023-robustness">
<titleInfo>
<title>Robustness of Multi-Source MT to Transcription Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Macháček</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Polák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raj</namePart>
<namePart type="family">Dabre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling. In this paper, we hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain. To this end, we first show that on a 10-hour ESIC corpus, the ASR errors in the original English speech and its simultaneous interpreting into German and Czech are mutually independent. We then use two sources, English and German, in a multi-source setting for translation into Czech to establish its robustness to ASR errors. Furthermore, we observe this robustness when translating both noisy sources together in a simultaneous translation setting. Our results show that multi-source neural machine translation has the potential to be useful in a real-time simultaneous translation setting, thereby motivating further investigation in this area.</abstract>
<identifier type="citekey">machacek-etal-2023-robustness</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.228</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.228</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>3707</start>
<end>3723</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robustness of Multi-Source MT to Transcription Errors
%A Macháček, Dominik
%A Polák, Peter
%A Bojar, Ondřej
%A Dabre, Raj
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F machacek-etal-2023-robustness
%X Automatic speech translation is sensitive to speech recognition errors, but in a multilingual scenario, the same content may be available in various languages via simultaneous interpreting, dubbing or subtitling. In this paper, we hypothesize that leveraging multiple sources will improve translation quality if the sources complement one another in terms of correct information they contain. To this end, we first show that on a 10-hour ESIC corpus, the ASR errors in the original English speech and its simultaneous interpreting into German and Czech are mutually independent. We then use two sources, English and German, in a multi-source setting for translation into Czech to establish its robustness to ASR errors. Furthermore, we observe this robustness when translating both noisy sources together in a simultaneous translation setting. Our results show that multi-source neural machine translation has the potential to be useful in a real-time simultaneous translation setting, thereby motivating further investigation in this area.
%R 10.18653/v1/2023.findings-acl.228
%U https://aclanthology.org/2023.findings-acl.228
%U https://doi.org/10.18653/v1/2023.findings-acl.228
%P 3707-3723
Markdown (Informal)
[Robustness of Multi-Source MT to Transcription Errors](https://aclanthology.org/2023.findings-acl.228) (Macháček et al., Findings 2023)
ACL
- Dominik Macháček, Peter Polák, Ondřej Bojar, and Raj Dabre. 2023. Robustness of Multi-Source MT to Transcription Errors. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3707–3723, Toronto, Canada. Association for Computational Linguistics.