@inproceedings{scarton-specia-2016-reading,
title = "A Reading Comprehension Corpus for Machine Translation Evaluation",
author = "Scarton, Carolina and
Specia, Lucia",
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/L16-1579",
pages = "3652--3658",
abstract = "Effectively assessing Natural Language Processing output tasks is a challenge for research in the area. In the case of Machine Translation (MT), automatic metrics are usually preferred over human evaluation, given time and budget constraints. However, traditional automatic metrics (such as BLEU) are not reliable for absolute quality assessment of documents, often producing similar scores for documents translated by the same MT system. For scenarios where absolute labels are necessary for building models, such as document-level Quality Estimation, these metrics can not be fully trusted. In this paper, we introduce a corpus of reading comprehension tests based on machine translated documents, where we evaluate documents based on answers to questions by fluent speakers of the target language. We describe the process of creating such a resource, the experiment design and agreement between the test takers. Finally, we discuss ways to convert the reading comprehension test into document-level quality scores.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scarton-specia-2016-reading">
<titleInfo>
<title>A Reading Comprehension Corpus for Machine Translation Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Carolina</namePart>
<namePart type="family">Scarton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</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>Effectively assessing Natural Language Processing output tasks is a challenge for research in the area. In the case of Machine Translation (MT), automatic metrics are usually preferred over human evaluation, given time and budget constraints. However, traditional automatic metrics (such as BLEU) are not reliable for absolute quality assessment of documents, often producing similar scores for documents translated by the same MT system. For scenarios where absolute labels are necessary for building models, such as document-level Quality Estimation, these metrics can not be fully trusted. In this paper, we introduce a corpus of reading comprehension tests based on machine translated documents, where we evaluate documents based on answers to questions by fluent speakers of the target language. We describe the process of creating such a resource, the experiment design and agreement between the test takers. Finally, we discuss ways to convert the reading comprehension test into document-level quality scores.</abstract>
<identifier type="citekey">scarton-specia-2016-reading</identifier>
<location>
<url>https://aclanthology.org/L16-1579</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3652</start>
<end>3658</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Reading Comprehension Corpus for Machine Translation Evaluation
%A Scarton, Carolina
%A Specia, Lucia
%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 scarton-specia-2016-reading
%X Effectively assessing Natural Language Processing output tasks is a challenge for research in the area. In the case of Machine Translation (MT), automatic metrics are usually preferred over human evaluation, given time and budget constraints. However, traditional automatic metrics (such as BLEU) are not reliable for absolute quality assessment of documents, often producing similar scores for documents translated by the same MT system. For scenarios where absolute labels are necessary for building models, such as document-level Quality Estimation, these metrics can not be fully trusted. In this paper, we introduce a corpus of reading comprehension tests based on machine translated documents, where we evaluate documents based on answers to questions by fluent speakers of the target language. We describe the process of creating such a resource, the experiment design and agreement between the test takers. Finally, we discuss ways to convert the reading comprehension test into document-level quality scores.
%U https://aclanthology.org/L16-1579
%P 3652-3658
Markdown (Informal)
[A Reading Comprehension Corpus for Machine Translation Evaluation](https://aclanthology.org/L16-1579) (Scarton & Specia, LREC 2016)
ACL