@inproceedings{popovic-arcan-2016-pe2rr,
title = "{PE}2rr Corpus: Manual Error Annotation of Automatically Pre-annotated {MT} Post-edits",
author = "Popovi{\'c}, Maja and
Ar{\v{c}}an, Mihael",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1005",
pages = "27--32",
abstract = "We present a freely available corpus containing source language texts from different domains along with their automatically generated translations into several distinct morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations. We believe that the corpus will be useful for many different applications. The main advantage of the approach used for creation of the corpus is the fusion of post-editing and error classification tasks, which have usually been seen as two independent tasks, although naturally they are not. We also show benefits of coupling automatic and manual error classification which facilitates the complex manual error annotation task as well as the development of automatic error classification tools. In addition, the approach facilitates annotation of language pair related issues.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popovic-arcan-2016-pe2rr">
<titleInfo>
<title>PE2rr Corpus: Manual Error Annotation of Automatically Pre-annotated MT Post-edits</title>
</titleInfo>
<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">Mihael</namePart>
<namePart type="family">Arčan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a freely available corpus containing source language texts from different domains along with their automatically generated translations into several distinct morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations. We believe that the corpus will be useful for many different applications. The main advantage of the approach used for creation of the corpus is the fusion of post-editing and error classification tasks, which have usually been seen as two independent tasks, although naturally they are not. We also show benefits of coupling automatic and manual error classification which facilitates the complex manual error annotation task as well as the development of automatic error classification tools. In addition, the approach facilitates annotation of language pair related issues.</abstract>
<identifier type="citekey">popovic-arcan-2016-pe2rr</identifier>
<location>
<url>https://aclanthology.org/L16-1005</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>27</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PE2rr Corpus: Manual Error Annotation of Automatically Pre-annotated MT Post-edits
%A Popović, Maja
%A Arčan, Mihael
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F popovic-arcan-2016-pe2rr
%X We present a freely available corpus containing source language texts from different domains along with their automatically generated translations into several distinct morphologically rich languages, their post-edited versions, and error annotations of the performed post-edit operations. We believe that the corpus will be useful for many different applications. The main advantage of the approach used for creation of the corpus is the fusion of post-editing and error classification tasks, which have usually been seen as two independent tasks, although naturally they are not. We also show benefits of coupling automatic and manual error classification which facilitates the complex manual error annotation task as well as the development of automatic error classification tools. In addition, the approach facilitates annotation of language pair related issues.
%U https://aclanthology.org/L16-1005
%P 27-32
Markdown (Informal)
[PE2rr Corpus: Manual Error Annotation of Automatically Pre-annotated MT Post-edits](https://aclanthology.org/L16-1005) (Popović & Arčan, LREC 2016)
ACL