@inproceedings{macketanz-etal-2021-linguistic,
title = "Linguistic Evaluation for the 2021 State-of-the-art Machine Translation Systems for {G}erman to {E}nglish and {E}nglish to {G}erman",
author = {Macketanz, Vivien and
Avramidis, Eleftherios and
Manakhimova, Shushen and
M{\"o}ller, Sebastian},
editor = "Barrault, Loic and
Bojar, Ondrej and
Bougares, Fethi and
Chatterjee, Rajen and
Costa-jussa, Marta R. and
Federmann, Christian and
Fishel, Mark and
Fraser, Alexander and
Freitag, Markus and
Graham, Yvette and
Grundkiewicz, Roman and
Guzman, Paco and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Kocmi, Tom and
Martins, Andre and
Morishita, Makoto and
Monz, Christof",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.115",
pages = "1059--1073",
abstract = "We are using a semi-automated test suite in order to provide a fine-grained linguistic evaluation for state-of-the-art machine translation systems. The evaluation includes 18 German to English and 18 English to German systems, submitted to the Translation Shared Task of the 2021 Conference on Machine Translation. Our submission adds up to the submissions of the previous years by creating and applying a wide-range test suite for English to German as a new language pair. The fine-grained evaluation allows spotting significant differences between systems that cannot be distinguished by the direct assessment of the human evaluation campaign. We find that most of the systems achieve good accuracies in the majority of linguistic phenomena but there are few phenomena with lower accuracy, such as the idioms, the modal pluperfect and the German resultative predicates. Two systems have significantly better test suite accuracy in macro-average in every language direction, Online-W and Facebook-AI for German to English and VolcTrans and Online-W for English to German. The systems show a steady improvement as compared to previous years.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macketanz-etal-2021-linguistic">
<titleInfo>
<title>Linguistic Evaluation for the 2021 State-of-the-art Machine Translation Systems for German to English and English to German</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivien</namePart>
<namePart type="family">Macketanz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eleftherios</namePart>
<namePart type="family">Avramidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shushen</namePart>
<namePart type="family">Manakhimova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loic</namePart>
<namePart type="family">Barrault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondrej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Grundkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paco</namePart>
<namePart type="family">Guzman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Morishita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We are using a semi-automated test suite in order to provide a fine-grained linguistic evaluation for state-of-the-art machine translation systems. The evaluation includes 18 German to English and 18 English to German systems, submitted to the Translation Shared Task of the 2021 Conference on Machine Translation. Our submission adds up to the submissions of the previous years by creating and applying a wide-range test suite for English to German as a new language pair. The fine-grained evaluation allows spotting significant differences between systems that cannot be distinguished by the direct assessment of the human evaluation campaign. We find that most of the systems achieve good accuracies in the majority of linguistic phenomena but there are few phenomena with lower accuracy, such as the idioms, the modal pluperfect and the German resultative predicates. Two systems have significantly better test suite accuracy in macro-average in every language direction, Online-W and Facebook-AI for German to English and VolcTrans and Online-W for English to German. The systems show a steady improvement as compared to previous years.</abstract>
<identifier type="citekey">macketanz-etal-2021-linguistic</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.115</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1059</start>
<end>1073</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Linguistic Evaluation for the 2021 State-of-the-art Machine Translation Systems for German to English and English to German
%A Macketanz, Vivien
%A Avramidis, Eleftherios
%A Manakhimova, Shushen
%A Möller, Sebastian
%Y Barrault, Loic
%Y Bojar, Ondrej
%Y Bougares, Fethi
%Y Chatterjee, Rajen
%Y Costa-jussa, Marta R.
%Y Federmann, Christian
%Y Fishel, Mark
%Y Fraser, Alexander
%Y Freitag, Markus
%Y Graham, Yvette
%Y Grundkiewicz, Roman
%Y Guzman, Paco
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Kocmi, Tom
%Y Martins, Andre
%Y Morishita, Makoto
%Y Monz, Christof
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F macketanz-etal-2021-linguistic
%X We are using a semi-automated test suite in order to provide a fine-grained linguistic evaluation for state-of-the-art machine translation systems. The evaluation includes 18 German to English and 18 English to German systems, submitted to the Translation Shared Task of the 2021 Conference on Machine Translation. Our submission adds up to the submissions of the previous years by creating and applying a wide-range test suite for English to German as a new language pair. The fine-grained evaluation allows spotting significant differences between systems that cannot be distinguished by the direct assessment of the human evaluation campaign. We find that most of the systems achieve good accuracies in the majority of linguistic phenomena but there are few phenomena with lower accuracy, such as the idioms, the modal pluperfect and the German resultative predicates. Two systems have significantly better test suite accuracy in macro-average in every language direction, Online-W and Facebook-AI for German to English and VolcTrans and Online-W for English to German. The systems show a steady improvement as compared to previous years.
%U https://aclanthology.org/2021.wmt-1.115
%P 1059-1073
Markdown (Informal)
[Linguistic Evaluation for the 2021 State-of-the-art Machine Translation Systems for German to English and English to German](https://aclanthology.org/2021.wmt-1.115) (Macketanz et al., WMT 2021)
ACL