@inproceedings{zhou-etal-2019-source,
title = "{SOURCE}: {SOUR}ce-Conditional Elmo-style Model for Machine Translation Quality Estimation",
author = "Zhou, Junpei and
Zhang, Zhisong and
Hu, Zecong",
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/W19-5411",
doi = "10.18653/v1/W19-5411",
pages = "106--111",
abstract = "Quality estimation (QE) of machine translation (MT) systems is a task of growing importance. It reduces the cost of post-editing, allowing machine-translated text to be used in formal occasions. In this work, we describe our submission system in WMT 2019 sentence-level QE task. We mainly explore the utilization of pre-trained translation models in QE and adopt a bi-directional translation-like strategy. The strategy is similar to ELMo, but additionally conditions on source sentences. Experiments on WMT QE dataset show that our strategy, which makes the pre-training slightly harder, can bring improvements for QE. In WMT-2019 QE task, our system ranked in the second place on En-De NMT dataset and the third place on En-Ru NMT dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2019-source">
<titleInfo>
<title>SOURCE: SOURce-Conditional Elmo-style Model for Machine Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junpei</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhisong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zecong</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Quality estimation (QE) of machine translation (MT) systems is a task of growing importance. It reduces the cost of post-editing, allowing machine-translated text to be used in formal occasions. In this work, we describe our submission system in WMT 2019 sentence-level QE task. We mainly explore the utilization of pre-trained translation models in QE and adopt a bi-directional translation-like strategy. The strategy is similar to ELMo, but additionally conditions on source sentences. Experiments on WMT QE dataset show that our strategy, which makes the pre-training slightly harder, can bring improvements for QE. In WMT-2019 QE task, our system ranked in the second place on En-De NMT dataset and the third place on En-Ru NMT dataset.</abstract>
<identifier type="citekey">zhou-etal-2019-source</identifier>
<identifier type="doi">10.18653/v1/W19-5411</identifier>
<location>
<url>https://aclanthology.org/W19-5411</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>106</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SOURCE: SOURce-Conditional Elmo-style Model for Machine Translation Quality Estimation
%A Zhou, Junpei
%A Zhang, Zhisong
%A Hu, Zecong
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F zhou-etal-2019-source
%X Quality estimation (QE) of machine translation (MT) systems is a task of growing importance. It reduces the cost of post-editing, allowing machine-translated text to be used in formal occasions. In this work, we describe our submission system in WMT 2019 sentence-level QE task. We mainly explore the utilization of pre-trained translation models in QE and adopt a bi-directional translation-like strategy. The strategy is similar to ELMo, but additionally conditions on source sentences. Experiments on WMT QE dataset show that our strategy, which makes the pre-training slightly harder, can bring improvements for QE. In WMT-2019 QE task, our system ranked in the second place on En-De NMT dataset and the third place on En-Ru NMT dataset.
%R 10.18653/v1/W19-5411
%U https://aclanthology.org/W19-5411
%U https://doi.org/10.18653/v1/W19-5411
%P 106-111
Markdown (Informal)
[SOURCE: SOURce-Conditional Elmo-style Model for Machine Translation Quality Estimation](https://aclanthology.org/W19-5411) (Zhou et al., 2019)
ACL