@inproceedings{turchi-negri-2014-automatic,
title = "Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements",
author = "Turchi, Marco and
Negri, Matteo",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/473_Paper.pdf",
pages = "1788--1792",
abstract = "The automatic estimation of machine translation (MT) output quality is an active research area due to its many potential applications (e.g. aiding human translation and post-editing, re-ranking MT hypotheses, MT system combination). Current approaches to the task rely on supervised learning methods for which high-quality labelled data is fundamental. In this framework, quality estimation (QE) has been mainly addressed as a regression problem where models trained on (source, target) sentence pairs annotated with continuous scores (in the [0-1] interval) are used to assign quality scores (in the same interval) to unseen data. Such definition of the problem assumes that continuous scores are informative and easily interpretable by different users. These assumptions, however, conflict with the subjectivity inherent to human translation and evaluation. On one side, the subjectivity of human judgements adds noise and biases to annotations based on scaled values. This problem reduces the usability of the resulting datasets, especially in application scenarios where a sharp distinction between good and bad translations is needed. On the other side, continuous scores are not always sufficient to decide whether a translation is actually acceptable or not. To overcome these issues, we present an automatic method for the annotation of (source, target) pairs with binary judgements that reflect an empirical, and easily interpretable notion of quality. The method is applied to annotate with binary judgements three QE datasets for different language combinations. The three datasets are combined in a single resource, called BinQE, which can be freely downloaded from \url{http://hlt.fbk.eu/technologies/binqe}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="turchi-negri-2014-automatic">
<titleInfo>
<title>Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The automatic estimation of machine translation (MT) output quality is an active research area due to its many potential applications (e.g. aiding human translation and post-editing, re-ranking MT hypotheses, MT system combination). Current approaches to the task rely on supervised learning methods for which high-quality labelled data is fundamental. In this framework, quality estimation (QE) has been mainly addressed as a regression problem where models trained on (source, target) sentence pairs annotated with continuous scores (in the [0-1] interval) are used to assign quality scores (in the same interval) to unseen data. Such definition of the problem assumes that continuous scores are informative and easily interpretable by different users. These assumptions, however, conflict with the subjectivity inherent to human translation and evaluation. On one side, the subjectivity of human judgements adds noise and biases to annotations based on scaled values. This problem reduces the usability of the resulting datasets, especially in application scenarios where a sharp distinction between good and bad translations is needed. On the other side, continuous scores are not always sufficient to decide whether a translation is actually acceptable or not. To overcome these issues, we present an automatic method for the annotation of (source, target) pairs with binary judgements that reflect an empirical, and easily interpretable notion of quality. The method is applied to annotate with binary judgements three QE datasets for different language combinations. The three datasets are combined in a single resource, called BinQE, which can be freely downloaded from http://hlt.fbk.eu/technologies/binqe.</abstract>
<identifier type="citekey">turchi-negri-2014-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/473_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1788</start>
<end>1792</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements
%A Turchi, Marco
%A Negri, Matteo
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F turchi-negri-2014-automatic
%X The automatic estimation of machine translation (MT) output quality is an active research area due to its many potential applications (e.g. aiding human translation and post-editing, re-ranking MT hypotheses, MT system combination). Current approaches to the task rely on supervised learning methods for which high-quality labelled data is fundamental. In this framework, quality estimation (QE) has been mainly addressed as a regression problem where models trained on (source, target) sentence pairs annotated with continuous scores (in the [0-1] interval) are used to assign quality scores (in the same interval) to unseen data. Such definition of the problem assumes that continuous scores are informative and easily interpretable by different users. These assumptions, however, conflict with the subjectivity inherent to human translation and evaluation. On one side, the subjectivity of human judgements adds noise and biases to annotations based on scaled values. This problem reduces the usability of the resulting datasets, especially in application scenarios where a sharp distinction between good and bad translations is needed. On the other side, continuous scores are not always sufficient to decide whether a translation is actually acceptable or not. To overcome these issues, we present an automatic method for the annotation of (source, target) pairs with binary judgements that reflect an empirical, and easily interpretable notion of quality. The method is applied to annotate with binary judgements three QE datasets for different language combinations. The three datasets are combined in a single resource, called BinQE, which can be freely downloaded from http://hlt.fbk.eu/technologies/binqe.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/473_Paper.pdf
%P 1788-1792
Markdown (Informal)
[Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements](http://www.lrec-conf.org/proceedings/lrec2014/pdf/473_Paper.pdf) (Turchi & Negri, LREC 2014)
ACL