@inproceedings{lapshinova-koltunski-etal-2022-dihutra-parallel,
title = "{D}i{H}u{T}ra: a Parallel Corpus to Analyse Differences between Human Translations",
author = "Lapshinova-Koltunski, Ekaterina and
Popovi{\'c}, Maja and
Koponen, Maarit",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.186/",
pages = "1751--1760",
abstract = "This paper describes a new corpus of human translations which contains both professional and students translations. The data consists of English sources {--} texts from news and reviews {--} and their translations into Russian and Croatian, as well as of the subcorpus containing translations of the review texts into Finnish. All target languages represent mid-resourced and less or mid-investigated ones. The corpus will be valuable for studying variation in translation as it allows a direct comparison between human translations of the same source texts. The corpus will also be a valuable resource for evaluating machine translation systems. We believe that this resource will facilitate understanding and improvement of the quality issues in both human and machine translation. In the paper, we describe how the data was collected, provide information on translator groups and summarise the differences between the human translations at hand based on our preliminary results with shallow features."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lapshinova-koltunski-etal-2022-dihutra-parallel">
<titleInfo>
<title>DiHuTra: a Parallel Corpus to Analyse Differences between Human Translations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Lapshinova-Koltunski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maja</namePart>
<namePart type="family">Popović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maarit</namePart>
<namePart type="family">Koponen</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 Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a new corpus of human translations which contains both professional and students translations. The data consists of English sources – texts from news and reviews – and their translations into Russian and Croatian, as well as of the subcorpus containing translations of the review texts into Finnish. All target languages represent mid-resourced and less or mid-investigated ones. The corpus will be valuable for studying variation in translation as it allows a direct comparison between human translations of the same source texts. The corpus will also be a valuable resource for evaluating machine translation systems. We believe that this resource will facilitate understanding and improvement of the quality issues in both human and machine translation. In the paper, we describe how the data was collected, provide information on translator groups and summarise the differences between the human translations at hand based on our preliminary results with shallow features.</abstract>
<identifier type="citekey">lapshinova-koltunski-etal-2022-dihutra-parallel</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.186/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1751</start>
<end>1760</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiHuTra: a Parallel Corpus to Analyse Differences between Human Translations
%A Lapshinova-Koltunski, Ekaterina
%A Popović, Maja
%A Koponen, Maarit
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lapshinova-koltunski-etal-2022-dihutra-parallel
%X This paper describes a new corpus of human translations which contains both professional and students translations. The data consists of English sources – texts from news and reviews – and their translations into Russian and Croatian, as well as of the subcorpus containing translations of the review texts into Finnish. All target languages represent mid-resourced and less or mid-investigated ones. The corpus will be valuable for studying variation in translation as it allows a direct comparison between human translations of the same source texts. The corpus will also be a valuable resource for evaluating machine translation systems. We believe that this resource will facilitate understanding and improvement of the quality issues in both human and machine translation. In the paper, we describe how the data was collected, provide information on translator groups and summarise the differences between the human translations at hand based on our preliminary results with shallow features.
%U https://aclanthology.org/2022.lrec-1.186/
%P 1751-1760
Markdown (Informal)
[DiHuTra: a Parallel Corpus to Analyse Differences between Human Translations](https://aclanthology.org/2022.lrec-1.186/) (Lapshinova-Koltunski et al., LREC 2022)
ACL