@inproceedings{scansani-dugast-2021-glossary,
title = "Glossary functionality in commercial machine translation: does it help? A first step to identify best practices for a language service provider",
author = {Scansani, Randy and
Dugast, Lo{\"\i}c},
editor = "Campbell, Janice and
Huyck, Ben and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of Machine Translation Summit XVIII: Users and Providers Track",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-up.8",
pages = "78--88",
abstract = "Recently, a number of commercial Machine Translation (MT) providers have started to offer glossary features allowing users to enforce terminology into the output of a generic model. However, to the best of our knowledge it is not clear how such features would impact terminology accuracy and the overall quality of the output. The present contribution aims at providing a first insight into the performance of the glossary-enhanced generic models offered by four providers. Our tests involve two different domains and language pairs, i.e. Sportswear En{--}Fr and Industrial Equipment De{--}En. The output of each generic model and of the glossaryenhanced one will be evaluated relying on Translation Error Rate (TER) to take into account the overall output quality and on accuracy to assess the compliance with the glossary. This is followed by a manual evaluation. The present contribution mainly focuses on understanding how these glossary features can be fruitfully exploited by language service providers (LSPs), especially in a scenario in which a customer glossary is already available and is added to the generic model as is.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scansani-dugast-2021-glossary">
<titleInfo>
<title>Glossary functionality in commercial machine translation: does it help? A first step to identify best practices for a language service provider</title>
</titleInfo>
<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>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Machine Translation Summit XVIII: Users and Providers Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Huyck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, a number of commercial Machine Translation (MT) providers have started to offer glossary features allowing users to enforce terminology into the output of a generic model. However, to the best of our knowledge it is not clear how such features would impact terminology accuracy and the overall quality of the output. The present contribution aims at providing a first insight into the performance of the glossary-enhanced generic models offered by four providers. Our tests involve two different domains and language pairs, i.e. Sportswear En–Fr and Industrial Equipment De–En. The output of each generic model and of the glossaryenhanced one will be evaluated relying on Translation Error Rate (TER) to take into account the overall output quality and on accuracy to assess the compliance with the glossary. This is followed by a manual evaluation. The present contribution mainly focuses on understanding how these glossary features can be fruitfully exploited by language service providers (LSPs), especially in a scenario in which a customer glossary is already available and is added to the generic model as is.</abstract>
<identifier type="citekey">scansani-dugast-2021-glossary</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-up.8</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Glossary functionality in commercial machine translation: does it help? A first step to identify best practices for a language service provider
%A Scansani, Randy
%A Dugast, Loïc
%Y Campbell, Janice
%Y Huyck, Ben
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of Machine Translation Summit XVIII: Users and Providers Track
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F scansani-dugast-2021-glossary
%X Recently, a number of commercial Machine Translation (MT) providers have started to offer glossary features allowing users to enforce terminology into the output of a generic model. However, to the best of our knowledge it is not clear how such features would impact terminology accuracy and the overall quality of the output. The present contribution aims at providing a first insight into the performance of the glossary-enhanced generic models offered by four providers. Our tests involve two different domains and language pairs, i.e. Sportswear En–Fr and Industrial Equipment De–En. The output of each generic model and of the glossaryenhanced one will be evaluated relying on Translation Error Rate (TER) to take into account the overall output quality and on accuracy to assess the compliance with the glossary. This is followed by a manual evaluation. The present contribution mainly focuses on understanding how these glossary features can be fruitfully exploited by language service providers (LSPs), especially in a scenario in which a customer glossary is already available and is added to the generic model as is.
%U https://aclanthology.org/2021.mtsummit-up.8
%P 78-88
Markdown (Informal)
[Glossary functionality in commercial machine translation: does it help? A first step to identify best practices for a language service provider](https://aclanthology.org/2021.mtsummit-up.8) (Scansani & Dugast, MTSummit 2021)
ACL