@inproceedings{nadejde-etal-2022-cocoa,
title = "{C}o{C}o{A}-{MT}: A Dataset and Benchmark for Contrastive Controlled {MT} with Application to Formality",
author = "Nadejde, Maria and
Currey, Anna and
Hsu, Benjamin and
Niu, Xing and
Federico, Marcello and
Dinu, Georgiana",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.47/",
doi = "10.18653/v1/2022.findings-naacl.47",
pages = "616--632",
abstract = "The machine translation (MT) task is typically formulated as that of returning a single translation for an input segment. However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended target audience, characteristics of the speaker, or even the relationship between speakers. Specific problems arise when dealing with honorifics, particularly translating from English into languages with formality markers. For example, the sentence {\textquotedblleft}Are you sure?{\textquotedblright} can be translated in German as {\textquotedblleft}Sind Sie sich sicher?{\textquotedblright} (formal register) or {\textquotedblleft}Bist du dir sicher?{\textquotedblright} (informal). Using wrong or inconsistent tone may be perceived as inappropriate or jarring for users of certain cultures and demographics. This work addresses the problem of learning to control target language attributes, in this case formality, from a small amount of labeled contrastive data. We introduce an annotated dataset (CoCoA-MT) and an associated evaluation metric for training and evaluating formality-controlled MT models for six diverse target languages. We show that we can train formality-controlled models by fine-tuning on labeled contrastive data, achieving high accuracy (82{\%} in-domain and 73{\%} out-of-domain) while maintaining overall quality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nadejde-etal-2022-cocoa">
<titleInfo>
<title>CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Nadejde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Currey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georgiana</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The machine translation (MT) task is typically formulated as that of returning a single translation for an input segment. However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended target audience, characteristics of the speaker, or even the relationship between speakers. Specific problems arise when dealing with honorifics, particularly translating from English into languages with formality markers. For example, the sentence “Are you sure?” can be translated in German as “Sind Sie sich sicher?” (formal register) or “Bist du dir sicher?” (informal). Using wrong or inconsistent tone may be perceived as inappropriate or jarring for users of certain cultures and demographics. This work addresses the problem of learning to control target language attributes, in this case formality, from a small amount of labeled contrastive data. We introduce an annotated dataset (CoCoA-MT) and an associated evaluation metric for training and evaluating formality-controlled MT models for six diverse target languages. We show that we can train formality-controlled models by fine-tuning on labeled contrastive data, achieving high accuracy (82% in-domain and 73% out-of-domain) while maintaining overall quality.</abstract>
<identifier type="citekey">nadejde-etal-2022-cocoa</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.47</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.47/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>616</start>
<end>632</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality
%A Nadejde, Maria
%A Currey, Anna
%A Hsu, Benjamin
%A Niu, Xing
%A Federico, Marcello
%A Dinu, Georgiana
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F nadejde-etal-2022-cocoa
%X The machine translation (MT) task is typically formulated as that of returning a single translation for an input segment. However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended target audience, characteristics of the speaker, or even the relationship between speakers. Specific problems arise when dealing with honorifics, particularly translating from English into languages with formality markers. For example, the sentence “Are you sure?” can be translated in German as “Sind Sie sich sicher?” (formal register) or “Bist du dir sicher?” (informal). Using wrong or inconsistent tone may be perceived as inappropriate or jarring for users of certain cultures and demographics. This work addresses the problem of learning to control target language attributes, in this case formality, from a small amount of labeled contrastive data. We introduce an annotated dataset (CoCoA-MT) and an associated evaluation metric for training and evaluating formality-controlled MT models for six diverse target languages. We show that we can train formality-controlled models by fine-tuning on labeled contrastive data, achieving high accuracy (82% in-domain and 73% out-of-domain) while maintaining overall quality.
%R 10.18653/v1/2022.findings-naacl.47
%U https://aclanthology.org/2022.findings-naacl.47/
%U https://doi.org/10.18653/v1/2022.findings-naacl.47
%P 616-632
Markdown (Informal)
[CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality](https://aclanthology.org/2022.findings-naacl.47/) (Nadejde et al., Findings 2022)
ACL