@inproceedings{zhang-van-genabith-2020-translation,
title = "Translation Quality Estimation by Jointly Learning to Score and Rank",
author = "Zhang, Jingyi and
van Genabith, Josef",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.205",
doi = "10.18653/v1/2020.emnlp-main.205",
pages = "2592--2598",
abstract = "The translation quality estimation (QE) task, particularly the QE as a Metric task, aims to evaluate the general quality of a translation based on the translation and the source sentence without using reference translations. Supervised learning of this QE task requires human evaluation of translation quality as training data. Human evaluation of translation quality can be performed in different ways, including assigning an absolute score to a translation or ranking different translations. In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations. Our QE model exploits cross-lingual sentence embeddings from pre-trained multilingual language models. We obtain new state-of-the-art results on the WMT 2019 QE as a Metric task and outperform sentBLEU on the WMT 2019 Metrics task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-van-genabith-2020-translation">
<titleInfo>
<title>Translation Quality Estimation by Jointly Learning to Score and Rank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jingyi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">van Genabith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The translation quality estimation (QE) task, particularly the QE as a Metric task, aims to evaluate the general quality of a translation based on the translation and the source sentence without using reference translations. Supervised learning of this QE task requires human evaluation of translation quality as training data. Human evaluation of translation quality can be performed in different ways, including assigning an absolute score to a translation or ranking different translations. In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations. Our QE model exploits cross-lingual sentence embeddings from pre-trained multilingual language models. We obtain new state-of-the-art results on the WMT 2019 QE as a Metric task and outperform sentBLEU on the WMT 2019 Metrics task.</abstract>
<identifier type="citekey">zhang-van-genabith-2020-translation</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.205</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.205</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2592</start>
<end>2598</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Translation Quality Estimation by Jointly Learning to Score and Rank
%A Zhang, Jingyi
%A van Genabith, Josef
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F zhang-van-genabith-2020-translation
%X The translation quality estimation (QE) task, particularly the QE as a Metric task, aims to evaluate the general quality of a translation based on the translation and the source sentence without using reference translations. Supervised learning of this QE task requires human evaluation of translation quality as training data. Human evaluation of translation quality can be performed in different ways, including assigning an absolute score to a translation or ranking different translations. In order to make use of different types of human evaluation data for supervised learning, we present a multi-task learning QE model that jointly learns two tasks: score a translation and rank two translations. Our QE model exploits cross-lingual sentence embeddings from pre-trained multilingual language models. We obtain new state-of-the-art results on the WMT 2019 QE as a Metric task and outperform sentBLEU on the WMT 2019 Metrics task.
%R 10.18653/v1/2020.emnlp-main.205
%U https://aclanthology.org/2020.emnlp-main.205
%U https://doi.org/10.18653/v1/2020.emnlp-main.205
%P 2592-2598
Markdown (Informal)
[Translation Quality Estimation by Jointly Learning to Score and Rank](https://aclanthology.org/2020.emnlp-main.205) (Zhang & van Genabith, EMNLP 2020)
ACL