@inproceedings{baek-etal-2020-patquest,
title = "{PATQUEST}: Papago Translation Quality Estimation",
author = "Baek, Yujin and
Kim, Zae Myung and
Moon, Jihyung and
Kim, Hyunjoong and
Park, Eunjeong",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.113",
pages = "991--998",
abstract = "This paper describes the system submitted by Papago team for the quality estimation task at WMT 2020. It proposes two key strategies for quality estimation: (1) task-specific pretraining scheme, and (2) task-specific data augmentation. The former focuses on devising learning signals for pretraining that are closely related to the downstream task. We also present data augmentation techniques that simulate the varying levels of errors that the downstream dataset may contain. Thus, our PATQUEST models are exposed to erroneous translations in both stages of task-specific pretraining and finetuning, effectively enhancing their generalization capability. Our submitted models achieve significant improvement over the baselines for Task 1 (Sentence-Level Direct Assessment; EN-DE only), and Task 3 (Document-Level Score).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baek-etal-2020-patquest">
<titleInfo>
<title>PATQUEST: Papago Translation Quality Estimation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yujin</namePart>
<namePart type="family">Baek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zae</namePart>
<namePart type="given">Myung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jihyung</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunjoong</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth 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 the system submitted by Papago team for the quality estimation task at WMT 2020. It proposes two key strategies for quality estimation: (1) task-specific pretraining scheme, and (2) task-specific data augmentation. The former focuses on devising learning signals for pretraining that are closely related to the downstream task. We also present data augmentation techniques that simulate the varying levels of errors that the downstream dataset may contain. Thus, our PATQUEST models are exposed to erroneous translations in both stages of task-specific pretraining and finetuning, effectively enhancing their generalization capability. Our submitted models achieve significant improvement over the baselines for Task 1 (Sentence-Level Direct Assessment; EN-DE only), and Task 3 (Document-Level Score).</abstract>
<identifier type="citekey">baek-etal-2020-patquest</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.113</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>991</start>
<end>998</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PATQUEST: Papago Translation Quality Estimation
%A Baek, Yujin
%A Kim, Zae Myung
%A Moon, Jihyung
%A Kim, Hyunjoong
%A Park, Eunjeong
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F baek-etal-2020-patquest
%X This paper describes the system submitted by Papago team for the quality estimation task at WMT 2020. It proposes two key strategies for quality estimation: (1) task-specific pretraining scheme, and (2) task-specific data augmentation. The former focuses on devising learning signals for pretraining that are closely related to the downstream task. We also present data augmentation techniques that simulate the varying levels of errors that the downstream dataset may contain. Thus, our PATQUEST models are exposed to erroneous translations in both stages of task-specific pretraining and finetuning, effectively enhancing their generalization capability. Our submitted models achieve significant improvement over the baselines for Task 1 (Sentence-Level Direct Assessment; EN-DE only), and Task 3 (Document-Level Score).
%U https://aclanthology.org/2020.wmt-1.113
%P 991-998
Markdown (Informal)
[PATQUEST: Papago Translation Quality Estimation](https://aclanthology.org/2020.wmt-1.113) (Baek et al., WMT 2020)
ACL
- Yujin Baek, Zae Myung Kim, Jihyung Moon, Hyunjoong Kim, and Eunjeong Park. 2020. PATQUEST: Papago Translation Quality Estimation. In Proceedings of the Fifth Conference on Machine Translation, pages 991–998, Online. Association for Computational Linguistics.