@inproceedings{fernicola-etal-2023-return,
title = "Return to the Source: Assessing Machine Translation Suitability",
author = "Fernicola, Francesco and
Bernardini, Silvia and
Garcea, Federico and
Ferraresi, Adriano and
Barr{\'o}n-Cede{\~n}o, Alberto",
editor = "Nurminen, Mary and
Brenner, Judith and
Koponen, Maarit and
Latomaa, Sirkku and
Mikhailov, Mikhail and
Schierl, Frederike and
Ranasinghe, Tharindu and
Vanmassenhove, Eva and
Vidal, Sergi Alvarez and
Aranberri, Nora and
Nunziatini, Mara and
Escart{\'\i}n, Carla Parra and
Forcada, Mikel and
Popovic, Maja and
Scarton, Carolina and
Moniz, Helena",
booktitle = "Proceedings of the 24th Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2023",
address = "Tampere, Finland",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2023.eamt-1.9",
pages = "79--89",
abstract = "We approach the task of assessing the suitability of a source text for translation by transferring the knowledge from established MT evaluation metrics to a model able to predict MT quality a priori from the source text alone. To open the door to experiments in this regard, we depart from reference English-German parallel corpora to build a corpus of 14,253 source text-quality score tuples. The tuples include four state-of-the-art metrics: cushLEPOR, BERTScore, COMET, and TransQuest. With this new resource at hand, we fine-tune XLM-RoBERTa, both in a single-task and a multi-task setting, to predict these evaluation scores from the source text alone. Results for this methodology are promising, with the single-task model able to approximate well-established MT evaluation and quality estimation metrics - without looking at the actual machine translations - achieving low RMSE values in the [0.1-0.2] range and Pearson correlation scores up to 0.688.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernicola-etal-2023-return">
<titleInfo>
<title>Return to the Source: Assessing Machine Translation Suitability</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Fernicola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Bernardini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Garcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriano</namePart>
<namePart type="family">Ferraresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Barrón-Cedeño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<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">Judith</namePart>
<namePart type="family">Brenner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirkku</namePart>
<namePart type="family">Latomaa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikhail</namePart>
<namePart type="family">Mikhailov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederike</namePart>
<namePart type="family">Schierl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tharindu</namePart>
<namePart type="family">Ranasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eva</namePart>
<namePart type="family">Vanmassenhove</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergi</namePart>
<namePart type="given">Alvarez</namePart>
<namePart type="family">Vidal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nora</namePart>
<namePart type="family">Aranberri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mara</namePart>
<namePart type="family">Nunziatini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popovic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Tampere, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We approach the task of assessing the suitability of a source text for translation by transferring the knowledge from established MT evaluation metrics to a model able to predict MT quality a priori from the source text alone. To open the door to experiments in this regard, we depart from reference English-German parallel corpora to build a corpus of 14,253 source text-quality score tuples. The tuples include four state-of-the-art metrics: cushLEPOR, BERTScore, COMET, and TransQuest. With this new resource at hand, we fine-tune XLM-RoBERTa, both in a single-task and a multi-task setting, to predict these evaluation scores from the source text alone. Results for this methodology are promising, with the single-task model able to approximate well-established MT evaluation and quality estimation metrics - without looking at the actual machine translations - achieving low RMSE values in the [0.1-0.2] range and Pearson correlation scores up to 0.688.</abstract>
<identifier type="citekey">fernicola-etal-2023-return</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.9</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>79</start>
<end>89</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Return to the Source: Assessing Machine Translation Suitability
%A Fernicola, Francesco
%A Bernardini, Silvia
%A Garcea, Federico
%A Ferraresi, Adriano
%A Barrón-Cedeño, Alberto
%Y Nurminen, Mary
%Y Brenner, Judith
%Y Koponen, Maarit
%Y Latomaa, Sirkku
%Y Mikhailov, Mikhail
%Y Schierl, Frederike
%Y Ranasinghe, Tharindu
%Y Vanmassenhove, Eva
%Y Vidal, Sergi Alvarez
%Y Aranberri, Nora
%Y Nunziatini, Mara
%Y Escartín, Carla Parra
%Y Forcada, Mikel
%Y Popovic, Maja
%Y Scarton, Carolina
%Y Moniz, Helena
%S Proceedings of the 24th Annual Conference of the European Association for Machine Translation
%D 2023
%8 June
%I European Association for Machine Translation
%C Tampere, Finland
%F fernicola-etal-2023-return
%X We approach the task of assessing the suitability of a source text for translation by transferring the knowledge from established MT evaluation metrics to a model able to predict MT quality a priori from the source text alone. To open the door to experiments in this regard, we depart from reference English-German parallel corpora to build a corpus of 14,253 source text-quality score tuples. The tuples include four state-of-the-art metrics: cushLEPOR, BERTScore, COMET, and TransQuest. With this new resource at hand, we fine-tune XLM-RoBERTa, both in a single-task and a multi-task setting, to predict these evaluation scores from the source text alone. Results for this methodology are promising, with the single-task model able to approximate well-established MT evaluation and quality estimation metrics - without looking at the actual machine translations - achieving low RMSE values in the [0.1-0.2] range and Pearson correlation scores up to 0.688.
%U https://aclanthology.org/2023.eamt-1.9
%P 79-89
Markdown (Informal)
[Return to the Source: Assessing Machine Translation Suitability](https://aclanthology.org/2023.eamt-1.9) (Fernicola et al., EAMT 2023)
ACL
- Francesco Fernicola, Silvia Bernardini, Federico Garcea, Adriano Ferraresi, and Alberto Barrón-Cedeño. 2023. Return to the Source: Assessing Machine Translation Suitability. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 79–89, Tampere, Finland. European Association for Machine Translation.