@inproceedings{goncalves-etal-2022-agent,
title = "Agent and User-Generated Content and its Impact on Customer Support {MT}",
author = "Gon{\c{c}}alves, Madalena and
Buchicchio, Marianna and
Stewart, Craig and
Moniz, Helena and
Lavie, Alon",
editor = {Moniz, Helena and
Macken, Lieve and
Rufener, Andrew and
Barrault, Lo{\"\i}c and
Costa-juss{\`a}, Marta R. and
Declercq, Christophe and
Koponen, Maarit and
Kemp, Ellie and
Pilos, Spyridon and
Forcada, Mikel L. and
Scarton, Carolina and
Van den Bogaert, Joachim and
Daems, Joke and
Tezcan, Arda and
Vanroy, Bram and
Fonteyne, Margot},
booktitle = "Proceedings of the 23rd Annual Conference of the European Association for Machine Translation",
month = jun,
year = "2022",
address = "Ghent, Belgium",
publisher = "European Association for Machine Translation",
url = "https://aclanthology.org/2022.eamt-1.23",
pages = "201--210",
abstract = "This paper illustrates a new evaluation framework developed at Unbabel for measuring the quality of source language text and its effect on both Machine Translation (MT) and Human Post-Edition (PE) performed by non-professional post-editors. We examine both agent and user-generated content from the Customer Support domain and propose that differentiating the two is crucial to obtaining high quality translation output. Furthermore, we present results of initial experimentation with a new evaluation typology based on the Multidimensional Quality Metrics (MQM) Framework Lommel et al., 2014), specifically tailored toward the evaluation of source language text. We show how the MQM Framework Lommel et al., 2014) can be adapted to assess errors of monolingual source texts and demonstrate how very specific source errors propagate to the MT and PE targets. Finally, we illustrate how MT systems are not robust enough to handle very specific source noise in the context of Customer Support data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goncalves-etal-2022-agent">
<titleInfo>
<title>Agent and User-Generated Content and its Impact on Customer Support MT</title>
</titleInfo>
<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">Marianna</namePart>
<namePart type="family">Buchicchio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Stewart</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>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lieve</namePart>
<namePart type="family">Macken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Rufener</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Barrault</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-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Declercq</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">Ellie</namePart>
<namePart type="family">Kemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spyridon</namePart>
<namePart type="family">Pilos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</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">Joachim</namePart>
<namePart type="family">Van den Bogaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joke</namePart>
<namePart type="family">Daems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Tezcan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">Vanroy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margot</namePart>
<namePart type="family">Fonteyne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Ghent, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper illustrates a new evaluation framework developed at Unbabel for measuring the quality of source language text and its effect on both Machine Translation (MT) and Human Post-Edition (PE) performed by non-professional post-editors. We examine both agent and user-generated content from the Customer Support domain and propose that differentiating the two is crucial to obtaining high quality translation output. Furthermore, we present results of initial experimentation with a new evaluation typology based on the Multidimensional Quality Metrics (MQM) Framework Lommel et al., 2014), specifically tailored toward the evaluation of source language text. We show how the MQM Framework Lommel et al., 2014) can be adapted to assess errors of monolingual source texts and demonstrate how very specific source errors propagate to the MT and PE targets. Finally, we illustrate how MT systems are not robust enough to handle very specific source noise in the context of Customer Support data.</abstract>
<identifier type="citekey">goncalves-etal-2022-agent</identifier>
<location>
<url>https://aclanthology.org/2022.eamt-1.23</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>201</start>
<end>210</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Agent and User-Generated Content and its Impact on Customer Support MT
%A Gonçalves, Madalena
%A Buchicchio, Marianna
%A Stewart, Craig
%A Moniz, Helena
%A Lavie, Alon
%Y Moniz, Helena
%Y Macken, Lieve
%Y Rufener, Andrew
%Y Barrault, Loïc
%Y Costa-jussà, Marta R.
%Y Declercq, Christophe
%Y Koponen, Maarit
%Y Kemp, Ellie
%Y Pilos, Spyridon
%Y Forcada, Mikel L.
%Y Scarton, Carolina
%Y Van den Bogaert, Joachim
%Y Daems, Joke
%Y Tezcan, Arda
%Y Vanroy, Bram
%Y Fonteyne, Margot
%S Proceedings of the 23rd Annual Conference of the European Association for Machine Translation
%D 2022
%8 June
%I European Association for Machine Translation
%C Ghent, Belgium
%F goncalves-etal-2022-agent
%X This paper illustrates a new evaluation framework developed at Unbabel for measuring the quality of source language text and its effect on both Machine Translation (MT) and Human Post-Edition (PE) performed by non-professional post-editors. We examine both agent and user-generated content from the Customer Support domain and propose that differentiating the two is crucial to obtaining high quality translation output. Furthermore, we present results of initial experimentation with a new evaluation typology based on the Multidimensional Quality Metrics (MQM) Framework Lommel et al., 2014), specifically tailored toward the evaluation of source language text. We show how the MQM Framework Lommel et al., 2014) can be adapted to assess errors of monolingual source texts and demonstrate how very specific source errors propagate to the MT and PE targets. Finally, we illustrate how MT systems are not robust enough to handle very specific source noise in the context of Customer Support data.
%U https://aclanthology.org/2022.eamt-1.23
%P 201-210
Markdown (Informal)
[Agent and User-Generated Content and its Impact on Customer Support MT](https://aclanthology.org/2022.eamt-1.23) (Gonçalves et al., EAMT 2022)
ACL