@inproceedings{wisniewski-etal-2024-fame,
title = "{FAME}-{MT} Dataset: Formality Awareness Made Easy for Machine Translation Purposes",
author = "Wisniewski, Dawid and
Rostek, Zofia and
Nowakowski, Artur",
editor = "Scarton, Carolina and
Prescott, Charlotte and
Bayliss, Chris and
Oakley, Chris and
Wright, Joanna and
Wrigley, Stuart and
Song, Xingyi and
Gow-Smith, Edward and
Bawden, Rachel and
S{\'a}nchez-Cartagena, V{\'\i}ctor M and
Cadwell, Patrick and
Lapshinova-Koltunski, Ekaterina and
Cabarr{\~a}o, Vera and
Chatzitheodorou, Konstantinos and
Nurminen, Mary and
Kanojia, Diptesh and
Moniz, Helena",
booktitle = "Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)",
month = jun,
year = "2024",
address = "Sheffield, UK",
publisher = "European Association for Machine Translation (EAMT)",
url = "https://aclanthology.org/2024.eamt-1.16",
pages = "164--180",
abstract = "People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-generated translations and present $\textbf{FAME-MT}$ {--} a dataset consisting of 11.2 million translations between 15 European source languages and 8 European target languages classified to formal and informal classes according to target sentence formality. This dataset can be used to fine-tune machine translation models to ensure a given formality level for 8 European target languages considered. We describe the dataset creation procedure, the analysis of the dataset{'}s quality showing that $\textbf{FAME-MT}$ is a reliable source of language register information, and we construct a publicly available proof-of-concept machine translation model that uses the dataset to steer the formality level of the translation. Currently, it is the largest dataset of formality annotations, with examples expressed in 112 European language pairs. The dataset is made available online.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wisniewski-etal-2024-fame">
<titleInfo>
<title>FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Wisniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zofia</namePart>
<namePart type="family">Rostek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artur</namePart>
<namePart type="family">Nowakowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlotte</namePart>
<namePart type="family">Prescott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Bayliss</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Oakley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Wright</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stuart</namePart>
<namePart type="family">Wrigley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Gow-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Bawden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Víctor</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Sánchez-Cartagena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Cadwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Cabarrão</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="family">Chatzitheodorou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diptesh</namePart>
<namePart type="family">Kanojia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation (EAMT)</publisher>
<place>
<placeTerm type="text">Sheffield, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-generated translations and present FAME-MT – a dataset consisting of 11.2 million translations between 15 European source languages and 8 European target languages classified to formal and informal classes according to target sentence formality. This dataset can be used to fine-tune machine translation models to ensure a given formality level for 8 European target languages considered. We describe the dataset creation procedure, the analysis of the dataset’s quality showing that FAME-MT is a reliable source of language register information, and we construct a publicly available proof-of-concept machine translation model that uses the dataset to steer the formality level of the translation. Currently, it is the largest dataset of formality annotations, with examples expressed in 112 European language pairs. The dataset is made available online.</abstract>
<identifier type="citekey">wisniewski-etal-2024-fame</identifier>
<location>
<url>https://aclanthology.org/2024.eamt-1.16</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>164</start>
<end>180</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes
%A Wisniewski, Dawid
%A Rostek, Zofia
%A Nowakowski, Artur
%Y Scarton, Carolina
%Y Prescott, Charlotte
%Y Bayliss, Chris
%Y Oakley, Chris
%Y Wright, Joanna
%Y Wrigley, Stuart
%Y Song, Xingyi
%Y Gow-Smith, Edward
%Y Bawden, Rachel
%Y Sánchez-Cartagena, Víctor M.
%Y Cadwell, Patrick
%Y Lapshinova-Koltunski, Ekaterina
%Y Cabarrão, Vera
%Y Chatzitheodorou, Konstantinos
%Y Nurminen, Mary
%Y Kanojia, Diptesh
%Y Moniz, Helena
%S Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
%D 2024
%8 June
%I European Association for Machine Translation (EAMT)
%C Sheffield, UK
%F wisniewski-etal-2024-fame
%X People use language for various purposes. Apart from sharing information, individuals may use it to express emotions or to show respect for another person. In this paper, we focus on the formality level of machine-generated translations and present FAME-MT – a dataset consisting of 11.2 million translations between 15 European source languages and 8 European target languages classified to formal and informal classes according to target sentence formality. This dataset can be used to fine-tune machine translation models to ensure a given formality level for 8 European target languages considered. We describe the dataset creation procedure, the analysis of the dataset’s quality showing that FAME-MT is a reliable source of language register information, and we construct a publicly available proof-of-concept machine translation model that uses the dataset to steer the formality level of the translation. Currently, it is the largest dataset of formality annotations, with examples expressed in 112 European language pairs. The dataset is made available online.
%U https://aclanthology.org/2024.eamt-1.16
%P 164-180
Markdown (Informal)
[FAME-MT Dataset: Formality Awareness Made Easy for Machine Translation Purposes](https://aclanthology.org/2024.eamt-1.16) (Wisniewski et al., EAMT 2024)
ACL