@inproceedings{heo-etal-2021-quality,
title = "Quality Estimation Using Dual Encoders with Transfer Learning",
author = "Heo, Dam and
Lee, WonKee and
Jung, Baikjin and
Lee, Jong-Hyeok",
booktitle = "Proceedings of the Sixth Conference on Machine Translation",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wmt-1.96",
pages = "920--927",
abstract = "This paper describes POSTECH{'}s quality estimation systems submitted to Task 2 of the WMT 2021 quality estimation shared task: Word and Sentence-Level Post-editing Effort. We notice that it is possible to improve the stability of the latest quality estimation models that have only one encoder based on the self-attention mechanism to simultaneously process both of the two input data, a source sequence and its machine translation, in that such models have neglected to take advantage of pre-trained monolingual representations, which are generally accepted as reliable representations for various natural language processing tasks. Therefore, our model uses two pre-trained monolingual encoders and then exchanges the information of two encoded representations through two additional cross attention networks. According to the official leaderboard, our systems outperform the baseline systems in terms of the Matthews correlation coefficient for machine translations{'} word-level quality estimation and in terms of the Pearson{'}s correlation coefficient for sentence-level quality estimation by 0.4126 and 0.5497 respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heo-etal-2021-quality">
<titleInfo>
<title>Quality Estimation Using Dual Encoders with Transfer Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dam</namePart>
<namePart type="family">Heo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">WonKee</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baikjin</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong-Hyeok</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes POSTECH’s quality estimation systems submitted to Task 2 of the WMT 2021 quality estimation shared task: Word and Sentence-Level Post-editing Effort. We notice that it is possible to improve the stability of the latest quality estimation models that have only one encoder based on the self-attention mechanism to simultaneously process both of the two input data, a source sequence and its machine translation, in that such models have neglected to take advantage of pre-trained monolingual representations, which are generally accepted as reliable representations for various natural language processing tasks. Therefore, our model uses two pre-trained monolingual encoders and then exchanges the information of two encoded representations through two additional cross attention networks. According to the official leaderboard, our systems outperform the baseline systems in terms of the Matthews correlation coefficient for machine translations’ word-level quality estimation and in terms of the Pearson’s correlation coefficient for sentence-level quality estimation by 0.4126 and 0.5497 respectively.</abstract>
<identifier type="citekey">heo-etal-2021-quality</identifier>
<location>
<url>https://aclanthology.org/2021.wmt-1.96</url>
</location>
<part>
<date>2021-nov</date>
<extent unit="page">
<start>920</start>
<end>927</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Quality Estimation Using Dual Encoders with Transfer Learning
%A Heo, Dam
%A Lee, WonKee
%A Jung, Baikjin
%A Lee, Jong-Hyeok
%S Proceedings of the Sixth Conference on Machine Translation
%D 2021
%8 nov
%I Association for Computational Linguistics
%C Online
%F heo-etal-2021-quality
%X This paper describes POSTECH’s quality estimation systems submitted to Task 2 of the WMT 2021 quality estimation shared task: Word and Sentence-Level Post-editing Effort. We notice that it is possible to improve the stability of the latest quality estimation models that have only one encoder based on the self-attention mechanism to simultaneously process both of the two input data, a source sequence and its machine translation, in that such models have neglected to take advantage of pre-trained monolingual representations, which are generally accepted as reliable representations for various natural language processing tasks. Therefore, our model uses two pre-trained monolingual encoders and then exchanges the information of two encoded representations through two additional cross attention networks. According to the official leaderboard, our systems outperform the baseline systems in terms of the Matthews correlation coefficient for machine translations’ word-level quality estimation and in terms of the Pearson’s correlation coefficient for sentence-level quality estimation by 0.4126 and 0.5497 respectively.
%U https://aclanthology.org/2021.wmt-1.96
%P 920-927
Markdown (Informal)
[Quality Estimation Using Dual Encoders with Transfer Learning](https://aclanthology.org/2021.wmt-1.96) (Heo et al., WMT 2021)
ACL