@inproceedings{freitag-etal-2022-natural,
title = "A Natural Diet: Towards Improving Naturalness of Machine Translation Output",
author = "Freitag, Markus and
Vilar, David and
Grangier, David and
Cherry, Colin and
Foster, George",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.263",
doi = "10.18653/v1/2022.findings-acl.263",
pages = "3340--3353",
abstract = "Machine translation (MT) evaluation often focuses on accuracy and fluency, without paying much attention to translation style. This means that, even when considered accurate and fluent, MT output can still sound less natural than high quality human translations or text originally written in the target language. Machine translation output notably exhibits lower lexical diversity, and employs constructs that mirror those in the source sentence. In this work we propose a method for training MT systems to achieve a more natural style, i.e. mirroring the style of text originally written in the target language. Our method tags parallel training data according to the naturalness of the target side by contrasting language models trained on natural and translated data. Tagging data allows us to put greater emphasis on target sentences originally written in the target language. Automatic metrics show that the resulting models achieve lexical richness on par with human translations, mimicking a style much closer to sentences originally written in the target language. Furthermore, we find that their output is preferred by human experts when compared to the baseline translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="freitag-etal-2022-natural">
<titleInfo>
<title>A Natural Diet: Towards Improving Naturalness of Machine Translation Output</title>
</titleInfo>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Vilar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Grangier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine translation (MT) evaluation often focuses on accuracy and fluency, without paying much attention to translation style. This means that, even when considered accurate and fluent, MT output can still sound less natural than high quality human translations or text originally written in the target language. Machine translation output notably exhibits lower lexical diversity, and employs constructs that mirror those in the source sentence. In this work we propose a method for training MT systems to achieve a more natural style, i.e. mirroring the style of text originally written in the target language. Our method tags parallel training data according to the naturalness of the target side by contrasting language models trained on natural and translated data. Tagging data allows us to put greater emphasis on target sentences originally written in the target language. Automatic metrics show that the resulting models achieve lexical richness on par with human translations, mimicking a style much closer to sentences originally written in the target language. Furthermore, we find that their output is preferred by human experts when compared to the baseline translations.</abstract>
<identifier type="citekey">freitag-etal-2022-natural</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.263</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.263</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>3340</start>
<end>3353</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Natural Diet: Towards Improving Naturalness of Machine Translation Output
%A Freitag, Markus
%A Vilar, David
%A Grangier, David
%A Cherry, Colin
%A Foster, George
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F freitag-etal-2022-natural
%X Machine translation (MT) evaluation often focuses on accuracy and fluency, without paying much attention to translation style. This means that, even when considered accurate and fluent, MT output can still sound less natural than high quality human translations or text originally written in the target language. Machine translation output notably exhibits lower lexical diversity, and employs constructs that mirror those in the source sentence. In this work we propose a method for training MT systems to achieve a more natural style, i.e. mirroring the style of text originally written in the target language. Our method tags parallel training data according to the naturalness of the target side by contrasting language models trained on natural and translated data. Tagging data allows us to put greater emphasis on target sentences originally written in the target language. Automatic metrics show that the resulting models achieve lexical richness on par with human translations, mimicking a style much closer to sentences originally written in the target language. Furthermore, we find that their output is preferred by human experts when compared to the baseline translations.
%R 10.18653/v1/2022.findings-acl.263
%U https://aclanthology.org/2022.findings-acl.263
%U https://doi.org/10.18653/v1/2022.findings-acl.263
%P 3340-3353
Markdown (Informal)
[A Natural Diet: Towards Improving Naturalness of Machine Translation Output](https://aclanthology.org/2022.findings-acl.263) (Freitag et al., Findings 2022)
ACL