@inproceedings{cabeca-etal-2023-quality,
title = "Quality Fit for Purpose: Building Business Critical Errors Test Suites",
author = "Cabe{\c{c}}a, Mariana and
Buchicchio, Marianna and
Gon{\c{c}}alves, Madalena and
Maroti, Christine and
Godinho, Jo{\~a}o and
Coelho, Pedro and
Moniz, Helena and
Lavie, Alon",
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-1.44",
pages = "451--460",
abstract = "This paper illustrates a new methodology based on Test Suites (Avramidis et al., 2018) with focus on Business Critical Errors (BCEs) (Stewart et al., 2022) to evaluate the output of Machine Translation (MT) and Quality Estimation (QE) systems. We demonstrate the value of relying on semi-automatic evaluation done through scalable BCE-focused Test Suites to monitor both MT and QE systems{'} performance for 8 language pairs (LPs) and a total of 4 error categories. This approach allows us to not only track the impact of new features and implementations in a real business environment, but also to identify strengths and weaknesses in models regarding different error types, and subsequently know what to improve henceforth.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cabeca-etal-2023-quality">
<titleInfo>
<title>Quality Fit for Purpose: Building Business Critical Errors Test Suites</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Cabeça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Buchicchio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madalena</namePart>
<namePart type="family">Gonçalves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Maroti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Godinho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Coelho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alon</namePart>
<namePart type="family">Lavie</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>This paper illustrates a new methodology based on Test Suites (Avramidis et al., 2018) with focus on Business Critical Errors (BCEs) (Stewart et al., 2022) to evaluate the output of Machine Translation (MT) and Quality Estimation (QE) systems. We demonstrate the value of relying on semi-automatic evaluation done through scalable BCE-focused Test Suites to monitor both MT and QE systems’ performance for 8 language pairs (LPs) and a total of 4 error categories. This approach allows us to not only track the impact of new features and implementations in a real business environment, but also to identify strengths and weaknesses in models regarding different error types, and subsequently know what to improve henceforth.</abstract>
<identifier type="citekey">cabeca-etal-2023-quality</identifier>
<location>
<url>https://aclanthology.org/2023.eamt-1.44</url>
</location>
<part>
<date>2023-06</date>
<extent unit="page">
<start>451</start>
<end>460</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Fit for Purpose: Building Business Critical Errors Test Suites
%A Cabeça, Mariana
%A Buchicchio, Marianna
%A Gonçalves, Madalena
%A Maroti, Christine
%A Godinho, João
%A Coelho, Pedro
%A Moniz, Helena
%A Lavie, Alon
%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 cabeca-etal-2023-quality
%X This paper illustrates a new methodology based on Test Suites (Avramidis et al., 2018) with focus on Business Critical Errors (BCEs) (Stewart et al., 2022) to evaluate the output of Machine Translation (MT) and Quality Estimation (QE) systems. We demonstrate the value of relying on semi-automatic evaluation done through scalable BCE-focused Test Suites to monitor both MT and QE systems’ performance for 8 language pairs (LPs) and a total of 4 error categories. This approach allows us to not only track the impact of new features and implementations in a real business environment, but also to identify strengths and weaknesses in models regarding different error types, and subsequently know what to improve henceforth.
%U https://aclanthology.org/2023.eamt-1.44
%P 451-460
Markdown (Informal)
[Quality Fit for Purpose: Building Business Critical Errors Test Suites](https://aclanthology.org/2023.eamt-1.44) (Cabeça et al., EAMT 2023)
ACL
- Mariana Cabeça, Marianna Buchicchio, Madalena Gonçalves, Christine Maroti, João Godinho, Pedro Coelho, Helena Moniz, and Alon Lavie. 2023. Quality Fit for Purpose: Building Business Critical Errors Test Suites. In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, pages 451–460, Tampere, Finland. European Association for Machine Translation.