@inproceedings{shterionov-etal-2019-ape,
title = "{APE} through Neural and Statistical {MT} with Augmented Data. {ADAPT}/{DCU} Submission to the {WMT} 2019 {APE} Shared Task",
author = "Shterionov, Dimitar and
Wagner, Joachim and
do Carmo, F{\'e}lix",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Martins, Andr{\'e} and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5415",
doi = "10.18653/v1/W19-5415",
pages = "132--138",
abstract = "Automatic post-editing (APE) can be reduced to a machine translation (MT) task, where the source is the output of a specific MT system and the target is its post-edited variant. However, this approach does not consider context information that can be found in the original source of the MT system. Thus a better approach is to employ multi-source MT, where two input sequences are considered {--} the one being the original source and the other being the MT output. Extra context information can be introduced in the form of extra tokens that identify certain global property of a group of segments, added as a prefix or a suffix to each segment. Successfully applied in domain adaptation of MT as well as on APE, this technique deserves further attention. In this work we investigate multi-source neural APE (or NPE) systems with training data which has been augmented with two types of extra context tokens. We experiment with authentic and synthetic data provided by WMT 2019 and submit our results to the APE shared task. We also experiment with using statistical machine translation (SMT) methods for APE. While our systems score bellow the baseline, we consider this work a step towards understanding the added value of extra context in the case of APE.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shterionov-etal-2019-ape">
<titleInfo>
<title>APE through Neural and Statistical MT with Augmented Data. ADAPT/DCU Submission to the WMT 2019 APE Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Shterionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joachim</namePart>
<namePart type="family">Wagner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Félix</namePart>
<namePart type="family">do Carmo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Federmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Huck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="given">Jimeno</namePart>
<namePart type="family">Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aurélie</namePart>
<namePart type="family">Névéol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Neves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matt</namePart>
<namePart type="family">Post</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karin</namePart>
<namePart type="family">Verspoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic post-editing (APE) can be reduced to a machine translation (MT) task, where the source is the output of a specific MT system and the target is its post-edited variant. However, this approach does not consider context information that can be found in the original source of the MT system. Thus a better approach is to employ multi-source MT, where two input sequences are considered – the one being the original source and the other being the MT output. Extra context information can be introduced in the form of extra tokens that identify certain global property of a group of segments, added as a prefix or a suffix to each segment. Successfully applied in domain adaptation of MT as well as on APE, this technique deserves further attention. In this work we investigate multi-source neural APE (or NPE) systems with training data which has been augmented with two types of extra context tokens. We experiment with authentic and synthetic data provided by WMT 2019 and submit our results to the APE shared task. We also experiment with using statistical machine translation (SMT) methods for APE. While our systems score bellow the baseline, we consider this work a step towards understanding the added value of extra context in the case of APE.</abstract>
<identifier type="citekey">shterionov-etal-2019-ape</identifier>
<identifier type="doi">10.18653/v1/W19-5415</identifier>
<location>
<url>https://aclanthology.org/W19-5415</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>132</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T APE through Neural and Statistical MT with Augmented Data. ADAPT/DCU Submission to the WMT 2019 APE Shared Task
%A Shterionov, Dimitar
%A Wagner, Joachim
%A do Carmo, Félix
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Martins, André
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F shterionov-etal-2019-ape
%X Automatic post-editing (APE) can be reduced to a machine translation (MT) task, where the source is the output of a specific MT system and the target is its post-edited variant. However, this approach does not consider context information that can be found in the original source of the MT system. Thus a better approach is to employ multi-source MT, where two input sequences are considered – the one being the original source and the other being the MT output. Extra context information can be introduced in the form of extra tokens that identify certain global property of a group of segments, added as a prefix or a suffix to each segment. Successfully applied in domain adaptation of MT as well as on APE, this technique deserves further attention. In this work we investigate multi-source neural APE (or NPE) systems with training data which has been augmented with two types of extra context tokens. We experiment with authentic and synthetic data provided by WMT 2019 and submit our results to the APE shared task. We also experiment with using statistical machine translation (SMT) methods for APE. While our systems score bellow the baseline, we consider this work a step towards understanding the added value of extra context in the case of APE.
%R 10.18653/v1/W19-5415
%U https://aclanthology.org/W19-5415
%U https://doi.org/10.18653/v1/W19-5415
%P 132-138
Markdown (Informal)
[APE through Neural and Statistical MT with Augmented Data. ADAPT/DCU Submission to the WMT 2019 APE Shared Task](https://aclanthology.org/W19-5415) (Shterionov et al., WMT 2019)
ACL