@inproceedings{gaona-etal-2023-quality,
title = "Quality Analysis of Multilingual Neural Machine Translation Systems and Reference Test Translations for the {E}nglish-{R}omanian language pair in the Medical Domain",
author = "Gaona, Miguel Angel Rios and
Chereji, Raluca-Maria and
Secara, Alina and
Ciobanu, Dragos",
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-1.35",
pages = "355--364",
abstract = "Multilingual Neural Machine Translation (MNMT) models allow to translate across multiple languages based on only one system. We study the quality of a domain-adapted MNMT model in the medical domain for English-Romanian with automatic metrics and a human error typology annotation based on the Multidimensional Quality Metrics (MQM). We further expand the MQM typology to include terminology-specific error categories. We compare the out-of-domain MNMT with the in-domain adapted MNMT on a standard test dataset of abstracts from medical publications. The in-domain MNMT model outperforms the out-of-domain MNMT in all measured automatic metrics and produces fewer errors. In addition, we perform the manual annotation over the reference test dataset to study the quality of the reference translations. We identify a high number of omissions, additions, and mistranslations in the reference dataset, and comment on the assumed accuracy of existing datasets. Finally, we compare the correlation between the COMET, BERTScore, and chrF automatic metrics with the MQM annotated translations. COMET shows a better correlation with the MQM scores compared to the other metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gaona-etal-2023-quality">
<titleInfo>
<title>Quality Analysis of Multilingual Neural Machine Translation Systems and Reference Test Translations for the English-Romanian language pair in the Medical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="given">Angel</namePart>
<namePart type="given">Rios</namePart>
<namePart type="family">Gaona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raluca-Maria</namePart>
<namePart type="family">Chereji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Secara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragos</namePart>
<namePart type="family">Ciobanu</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>Multilingual Neural Machine Translation (MNMT) models allow to translate across multiple languages based on only one system. We study the quality of a domain-adapted MNMT model in the medical domain for English-Romanian with automatic metrics and a human error typology annotation based on the Multidimensional Quality Metrics (MQM). We further expand the MQM typology to include terminology-specific error categories. We compare the out-of-domain MNMT with the in-domain adapted MNMT on a standard test dataset of abstracts from medical publications. The in-domain MNMT model outperforms the out-of-domain MNMT in all measured automatic metrics and produces fewer errors. In addition, we perform the manual annotation over the reference test dataset to study the quality of the reference translations. We identify a high number of omissions, additions, and mistranslations in the reference dataset, and comment on the assumed accuracy of existing datasets. Finally, we compare the correlation between the COMET, BERTScore, and chrF automatic metrics with the MQM annotated translations. COMET shows a better correlation with the MQM scores compared to the other metrics.</abstract>
<identifier type="citekey">gaona-etal-2023-quality</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.35</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>355</start>
<end>364</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Analysis of Multilingual Neural Machine Translation Systems and Reference Test Translations for the English-Romanian language pair in the Medical Domain
%A Gaona, Miguel Angel Rios
%A Chereji, Raluca-Maria
%A Secara, Alina
%A Ciobanu, Dragos
%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 gaona-etal-2023-quality
%X Multilingual Neural Machine Translation (MNMT) models allow to translate across multiple languages based on only one system. We study the quality of a domain-adapted MNMT model in the medical domain for English-Romanian with automatic metrics and a human error typology annotation based on the Multidimensional Quality Metrics (MQM). We further expand the MQM typology to include terminology-specific error categories. We compare the out-of-domain MNMT with the in-domain adapted MNMT on a standard test dataset of abstracts from medical publications. The in-domain MNMT model outperforms the out-of-domain MNMT in all measured automatic metrics and produces fewer errors. In addition, we perform the manual annotation over the reference test dataset to study the quality of the reference translations. We identify a high number of omissions, additions, and mistranslations in the reference dataset, and comment on the assumed accuracy of existing datasets. Finally, we compare the correlation between the COMET, BERTScore, and chrF automatic metrics with the MQM annotated translations. COMET shows a better correlation with the MQM scores compared to the other metrics.
%U https://aclanthology.org/2023.eamt-1.35
%P 355-364
Markdown (Informal)
[Quality Analysis of Multilingual Neural Machine Translation Systems and Reference Test Translations for the English-Romanian language pair in the Medical Domain](https://aclanthology.org/2023.eamt-1.35) (Gaona et al., EAMT 2023)
ACL