@inproceedings{macketanz-etal-2022-linguistically,
title = "A Linguistically Motivated Test Suite to Semi-Automatically Evaluate {G}erman{--}{E}nglish Machine Translation Output",
author = {Macketanz, Vivien and
Avramidis, Eleftherios and
Burchardt, Aljoscha and
Wang, He and
Ai, Renlong and
Manakhimova, Shushen and
Strohriegel, Ursula and
M{\"o}ller, Sebastian and
Uszkoreit, Hans},
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.99",
pages = "936--947",
abstract = "This paper presents a fine-grained test suite for the language pair German{--}English. The test suite is based on a number of linguistically motivated categories and phenomena and the semi-automatic evaluation is carried out with regular expressions. We describe the creation and implementation of the test suite in detail, providing a full list of all categories and phenomena. Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese{--}English. We describe how we tracked the development of the performance of various systems MT systems over the years with the help of the test suite and which categories and phenomena are prone to resulting in MT errors. For the first time, we also make a large part of our test suite publicly available to the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macketanz-etal-2022-linguistically">
<titleInfo>
<title>A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output</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">Aljoscha</namePart>
<namePart type="family">Burchardt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">He</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renlong</namePart>
<namePart type="family">Ai</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">Ursula</namePart>
<namePart type="family">Strohriegel</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>
<name type="personal">
<namePart type="given">Hans</namePart>
<namePart type="family">Uszkoreit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a fine-grained test suite for the language pair German–English. The test suite is based on a number of linguistically motivated categories and phenomena and the semi-automatic evaluation is carried out with regular expressions. We describe the creation and implementation of the test suite in detail, providing a full list of all categories and phenomena. Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese–English. We describe how we tracked the development of the performance of various systems MT systems over the years with the help of the test suite and which categories and phenomena are prone to resulting in MT errors. For the first time, we also make a large part of our test suite publicly available to the research community.</abstract>
<identifier type="citekey">macketanz-etal-2022-linguistically</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.99</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>936</start>
<end>947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output
%A Macketanz, Vivien
%A Avramidis, Eleftherios
%A Burchardt, Aljoscha
%A Wang, He
%A Ai, Renlong
%A Manakhimova, Shushen
%A Strohriegel, Ursula
%A Möller, Sebastian
%A Uszkoreit, Hans
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F macketanz-etal-2022-linguistically
%X This paper presents a fine-grained test suite for the language pair German–English. The test suite is based on a number of linguistically motivated categories and phenomena and the semi-automatic evaluation is carried out with regular expressions. We describe the creation and implementation of the test suite in detail, providing a full list of all categories and phenomena. Furthermore, we present various exemplary applications of our test suite that have been implemented in the past years, like contributions to the Conference of Machine Translation, the usage of the test suite and MT outputs for quality estimation, and the expansion of the test suite to the language pair Portuguese–English. We describe how we tracked the development of the performance of various systems MT systems over the years with the help of the test suite and which categories and phenomena are prone to resulting in MT errors. For the first time, we also make a large part of our test suite publicly available to the research community.
%U https://aclanthology.org/2022.lrec-1.99
%P 936-947
Markdown (Informal)
[A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output](https://aclanthology.org/2022.lrec-1.99) (Macketanz et al., LREC 2022)
ACL
- Vivien Macketanz, Eleftherios Avramidis, Aljoscha Burchardt, He Wang, Renlong Ai, Shushen Manakhimova, Ursula Strohriegel, Sebastian Möller, and Hans Uszkoreit. 2022. A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 936–947, Marseille, France. European Language Resources Association.