@inproceedings{qi-2019-nju,
title = "{NJU} Submissions for the {WMT}19 Quality Estimation Shared Task",
author = "Qi, Hou",
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/W19-5409",
doi = "10.18653/v1/W19-5409",
pages = "95--100",
abstract = "In this paper, we describe the submissions of the team from Nanjing University for the WMT19 sentence-level Quality Estimation (QE) shared task on English-German language pair. We develop two approaches based on a two-stage neural QE model consisting of a feature extractor and a quality estimator. More specifically, one of the proposed approaches employs the translation knowledge between the two languages from two different translation directions; while the other one employs extra monolingual knowledge from both source and target sides, obtained by pre-training deep self-attention networks. To efficiently train these two-stage models, a joint learning training method is applied. Experiments show that the ensemble model of the above two models achieves the best results on the benchmark dataset of the WMT17 sentence-level QE shared task and obtains competitive results in WMT19, ranking 3rd out of 10 submissions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-2019-nju">
<titleInfo>
<title>NJU Submissions for the WMT19 Quality Estimation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hou</namePart>
<namePart type="family">Qi</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>In this paper, we describe the submissions of the team from Nanjing University for the WMT19 sentence-level Quality Estimation (QE) shared task on English-German language pair. We develop two approaches based on a two-stage neural QE model consisting of a feature extractor and a quality estimator. More specifically, one of the proposed approaches employs the translation knowledge between the two languages from two different translation directions; while the other one employs extra monolingual knowledge from both source and target sides, obtained by pre-training deep self-attention networks. To efficiently train these two-stage models, a joint learning training method is applied. Experiments show that the ensemble model of the above two models achieves the best results on the benchmark dataset of the WMT17 sentence-level QE shared task and obtains competitive results in WMT19, ranking 3rd out of 10 submissions.</abstract>
<identifier type="citekey">qi-2019-nju</identifier>
<identifier type="doi">10.18653/v1/W19-5409</identifier>
<location>
<url>https://aclanthology.org/W19-5409</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>95</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NJU Submissions for the WMT19 Quality Estimation Shared Task
%A Qi, Hou
%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 qi-2019-nju
%X In this paper, we describe the submissions of the team from Nanjing University for the WMT19 sentence-level Quality Estimation (QE) shared task on English-German language pair. We develop two approaches based on a two-stage neural QE model consisting of a feature extractor and a quality estimator. More specifically, one of the proposed approaches employs the translation knowledge between the two languages from two different translation directions; while the other one employs extra monolingual knowledge from both source and target sides, obtained by pre-training deep self-attention networks. To efficiently train these two-stage models, a joint learning training method is applied. Experiments show that the ensemble model of the above two models achieves the best results on the benchmark dataset of the WMT17 sentence-level QE shared task and obtains competitive results in WMT19, ranking 3rd out of 10 submissions.
%R 10.18653/v1/W19-5409
%U https://aclanthology.org/W19-5409
%U https://doi.org/10.18653/v1/W19-5409
%P 95-100
Markdown (Informal)
[NJU Submissions for the WMT19 Quality Estimation Shared Task](https://aclanthology.org/W19-5409) (Qi, 2019)
ACL