@inproceedings{scansani-etal-2017-enhancing,
title = "Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources",
author = "Scansani, Randy and
Bernardini, Silvia and
Ferraresi, Adriano and
Gaspari, Federico and
Soffritti, Marcello",
editor = "Temnikova, Irina and
Orasan, Constantin and
Pastor, Gloria Corpas and
Vogel, Stephan",
booktitle = "Proceedings of the Workshop Human-Informed Translation and Interpreting Technology",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "Association for Computational Linguistics, Shoumen, Bulgaria",
url = "https://doi.org/10.26615/978-954-452-042-7_001",
doi = "10.26615/978-954-452-042-7_001",
pages = "1--10",
abstract = "This paper describes an approach to translating course unit descriptions from Italian and German into English, using a phrase-based machine translation (MT) system. The genre is very prominent among those requiring translation by universities in European countries in which English is a non-native language. For each language combination, an in-domain bilingual corpus including course unit and degree program descriptions is used to train an MT engine, whose output is then compared to a baseline engine trained on the Europarl corpus. In a subsequent experiment, a bilingual terminology database is added to the training sets in both engines and its impact on the output quality is evaluated based on BLEU and post-editing score. Results suggest that the use of domain-specific corpora boosts the engines quality for both language combinations, especially for German-English, whereas adding terminological resources does not seem to bring notable benefits.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scansani-etal-2017-enhancing">
<titleInfo>
<title>Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources</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">Silvia</namePart>
<namePart type="family">Bernardini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adriano</namePart>
<namePart type="family">Ferraresi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Gaspari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Soffritti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop Human-Informed Translation and Interpreting Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Temnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantin</namePart>
<namePart type="family">Orasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gloria</namePart>
<namePart type="given">Corpas</namePart>
<namePart type="family">Pastor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephan</namePart>
<namePart type="family">Vogel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics, Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes an approach to translating course unit descriptions from Italian and German into English, using a phrase-based machine translation (MT) system. The genre is very prominent among those requiring translation by universities in European countries in which English is a non-native language. For each language combination, an in-domain bilingual corpus including course unit and degree program descriptions is used to train an MT engine, whose output is then compared to a baseline engine trained on the Europarl corpus. In a subsequent experiment, a bilingual terminology database is added to the training sets in both engines and its impact on the output quality is evaluated based on BLEU and post-editing score. Results suggest that the use of domain-specific corpora boosts the engines quality for both language combinations, especially for German-English, whereas adding terminological resources does not seem to bring notable benefits.</abstract>
<identifier type="citekey">scansani-etal-2017-enhancing</identifier>
<identifier type="doi">10.26615/978-954-452-042-7_001</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources
%A Scansani, Randy
%A Bernardini, Silvia
%A Ferraresi, Adriano
%A Gaspari, Federico
%A Soffritti, Marcello
%Y Temnikova, Irina
%Y Orasan, Constantin
%Y Pastor, Gloria Corpas
%Y Vogel, Stephan
%S Proceedings of the Workshop Human-Informed Translation and Interpreting Technology
%D 2017
%8 September
%I Association for Computational Linguistics, Shoumen, Bulgaria
%C Varna, Bulgaria
%F scansani-etal-2017-enhancing
%X This paper describes an approach to translating course unit descriptions from Italian and German into English, using a phrase-based machine translation (MT) system. The genre is very prominent among those requiring translation by universities in European countries in which English is a non-native language. For each language combination, an in-domain bilingual corpus including course unit and degree program descriptions is used to train an MT engine, whose output is then compared to a baseline engine trained on the Europarl corpus. In a subsequent experiment, a bilingual terminology database is added to the training sets in both engines and its impact on the output quality is evaluated based on BLEU and post-editing score. Results suggest that the use of domain-specific corpora boosts the engines quality for both language combinations, especially for German-English, whereas adding terminological resources does not seem to bring notable benefits.
%R 10.26615/978-954-452-042-7_001
%U https://doi.org/10.26615/978-954-452-042-7_001
%P 1-10
Markdown (Informal)
[Enhancing Machine Translation of Academic Course Catalogues with Terminological Resources](https://doi.org/10.26615/978-954-452-042-7_001) (Scansani et al., RANLP 2017)
ACL