@inproceedings{afara-etal-2022-investigating,
title = "Investigating automatic and manual filtering methods to produce {MT}-ready glossaries from existing ones",
author = {Afara, Maria and
Scansani, Randy and
Dugast, Lo{\"i}c},
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-1.25/",
pages = "221--230",
abstract = "Commercial Machine Translation (MT) providers offer functionalities that allow users to leverage bilingual glossaries. This poses the question of how to turn glossaries that were intended to be used by a human translator into MT-ready ones, removing entries that could harm the MT output. We present two automatic filtering approaches - one based on rules and the second one relying on a translation memory - and a manual filtering procedure carried out by a linguist. The resulting glossaries are added to the MT model. The outputs are compared against a baseline where no glossary is used and an output produced using the original glossary. The present work aims at investigating if any of these filtering methods can bring a higher terminology accuracy without negative effects on the overall quality. Results are measured with terminology accuracy and Translation Edit Rate. We test our filters on two language pairs, En-Fr and De-En. Results show that some of the automatically filtered glossaries improve the output when compared to the baseline, and they may help reach a better balance between accuracy and overall quality, replacing the costly manual process without quality loss."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="afara-etal-2022-investigating">
<titleInfo>
<title>Investigating automatic and manual filtering methods to produce MT-ready glossaries from existing ones</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Afara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Randy</namePart>
<namePart type="family">Scansani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Dugast</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>Commercial Machine Translation (MT) providers offer functionalities that allow users to leverage bilingual glossaries. This poses the question of how to turn glossaries that were intended to be used by a human translator into MT-ready ones, removing entries that could harm the MT output. We present two automatic filtering approaches - one based on rules and the second one relying on a translation memory - and a manual filtering procedure carried out by a linguist. The resulting glossaries are added to the MT model. The outputs are compared against a baseline where no glossary is used and an output produced using the original glossary. The present work aims at investigating if any of these filtering methods can bring a higher terminology accuracy without negative effects on the overall quality. Results are measured with terminology accuracy and Translation Edit Rate. We test our filters on two language pairs, En-Fr and De-En. Results show that some of the automatically filtered glossaries improve the output when compared to the baseline, and they may help reach a better balance between accuracy and overall quality, replacing the costly manual process without quality loss.</abstract>
<identifier type="citekey">afara-etal-2022-investigating</identifier>
<location>
<url>https://aclanthology.org/2022.eamt-1.25/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>221</start>
<end>230</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating automatic and manual filtering methods to produce MT-ready glossaries from existing ones
%A Afara, Maria
%A Scansani, Randy
%A Dugast, Loïc
%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 afara-etal-2022-investigating
%X Commercial Machine Translation (MT) providers offer functionalities that allow users to leverage bilingual glossaries. This poses the question of how to turn glossaries that were intended to be used by a human translator into MT-ready ones, removing entries that could harm the MT output. We present two automatic filtering approaches - one based on rules and the second one relying on a translation memory - and a manual filtering procedure carried out by a linguist. The resulting glossaries are added to the MT model. The outputs are compared against a baseline where no glossary is used and an output produced using the original glossary. The present work aims at investigating if any of these filtering methods can bring a higher terminology accuracy without negative effects on the overall quality. Results are measured with terminology accuracy and Translation Edit Rate. We test our filters on two language pairs, En-Fr and De-En. Results show that some of the automatically filtered glossaries improve the output when compared to the baseline, and they may help reach a better balance between accuracy and overall quality, replacing the costly manual process without quality loss.
%U https://aclanthology.org/2022.eamt-1.25/
%P 221-230
Markdown (Informal)
[Investigating automatic and manual filtering methods to produce MT-ready glossaries from existing ones](https://aclanthology.org/2022.eamt-1.25/) (Afara et al., EAMT 2022)
ACL