@inproceedings{gaido-etal-2020-breeding,
title = "Breeding Gender-aware Direct Speech Translation Systems",
author = "Gaido, Marco and
Savoldi, Beatrice and
Bentivogli, Luisa and
Negri, Matteo and
Turchi, Marco",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.350",
doi = "10.18653/v1/2020.coling-main.350",
pages = "3951--3964",
abstract = "In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech audio data without intermediate transcription, direct ST models are able to leverage and preserve essential information present in the input (e.g.speaker{'}s vocal characteristics) that is otherwise lost in the cascade framework. Although such ability proved to be useful for gender translation, direct ST is nonetheless affected by gender bias just like its cascade counterpart, as well as machine translation and numerous other natural language processing applications. Moreover, direct ST systems that exclusively rely on vocal biometric features as a gender cue can be unsuitable or even potentially problematic for certain users. Going beyond speech signals, in this paper we compare different approaches to inform direct ST models about the speaker{'}s gender and test their ability to handle gender translation from English into Italian and French. To this aim, we manually annotated large datasets with speak-ers{'} gender information and used them for experiments reflecting different possible real-world scenarios. Our results show that gender-aware direct ST solutions can significantly outperform strong {--} but gender-unaware {--} direct ST models. In particular, the translation of gender-marked words can increase up to 30 points in accuracy while preserving overall translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaido-etal-2020-breeding">
<titleInfo>
<title>Breeding Gender-aware Direct Speech Translation Systems</title>
</titleInfo>
<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">Beatrice</namePart>
<namePart type="family">Savoldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">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>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech audio data without intermediate transcription, direct ST models are able to leverage and preserve essential information present in the input (e.g.speaker’s vocal characteristics) that is otherwise lost in the cascade framework. Although such ability proved to be useful for gender translation, direct ST is nonetheless affected by gender bias just like its cascade counterpart, as well as machine translation and numerous other natural language processing applications. Moreover, direct ST systems that exclusively rely on vocal biometric features as a gender cue can be unsuitable or even potentially problematic for certain users. Going beyond speech signals, in this paper we compare different approaches to inform direct ST models about the speaker’s gender and test their ability to handle gender translation from English into Italian and French. To this aim, we manually annotated large datasets with speak-ers’ gender information and used them for experiments reflecting different possible real-world scenarios. Our results show that gender-aware direct ST solutions can significantly outperform strong – but gender-unaware – direct ST models. In particular, the translation of gender-marked words can increase up to 30 points in accuracy while preserving overall translation quality.</abstract>
<identifier type="citekey">gaido-etal-2020-breeding</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.350</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.350</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3951</start>
<end>3964</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Breeding Gender-aware Direct Speech Translation Systems
%A Gaido, Marco
%A Savoldi, Beatrice
%A Bentivogli, Luisa
%A Negri, Matteo
%A Turchi, Marco
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F gaido-etal-2020-breeding
%X In automatic speech translation (ST), traditional cascade approaches involving separate transcription and translation steps are giving ground to increasingly competitive and more robust direct solutions. In particular, by translating speech audio data without intermediate transcription, direct ST models are able to leverage and preserve essential information present in the input (e.g.speaker’s vocal characteristics) that is otherwise lost in the cascade framework. Although such ability proved to be useful for gender translation, direct ST is nonetheless affected by gender bias just like its cascade counterpart, as well as machine translation and numerous other natural language processing applications. Moreover, direct ST systems that exclusively rely on vocal biometric features as a gender cue can be unsuitable or even potentially problematic for certain users. Going beyond speech signals, in this paper we compare different approaches to inform direct ST models about the speaker’s gender and test their ability to handle gender translation from English into Italian and French. To this aim, we manually annotated large datasets with speak-ers’ gender information and used them for experiments reflecting different possible real-world scenarios. Our results show that gender-aware direct ST solutions can significantly outperform strong – but gender-unaware – direct ST models. In particular, the translation of gender-marked words can increase up to 30 points in accuracy while preserving overall translation quality.
%R 10.18653/v1/2020.coling-main.350
%U https://aclanthology.org/2020.coling-main.350
%U https://doi.org/10.18653/v1/2020.coling-main.350
%P 3951-3964
Markdown (Informal)
[Breeding Gender-aware Direct Speech Translation Systems](https://aclanthology.org/2020.coling-main.350) (Gaido et al., COLING 2020)
ACL
- Marco Gaido, Beatrice Savoldi, Luisa Bentivogli, Matteo Negri, and Marco Turchi. 2020. Breeding Gender-aware Direct Speech Translation Systems. In Proceedings of the 28th International Conference on Computational Linguistics, pages 3951–3964, Barcelona, Spain (Online). International Committee on Computational Linguistics.