@inproceedings{moon-etal-2020-revisiting,
title = "Revisiting Round-trip Translation for Quality Estimation",
author = "Moon, Jihyung and
Cho, Hyunchang and
Park, Eunjeong L.",
editor = "Martins, Andr{\'e} and
Moniz, Helena and
Fumega, Sara and
Martins, Bruno and
Batista, Fernando and
Coheur, Luisa and
Parra, Carla and
Trancoso, Isabel and
Turchi, Marco and
Bisazza, Arianna and
Moorkens, Joss and
Guerberof, Ana and
Nurminen, Mary and
Marg, Lena and
Forcada, Mikel L.",
booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
month = nov,
year = "2020",
address = "Lisboa, Portugal",
publisher = "European Association for Machine Translation",
url = "http://aclanthology.org/2020.eamt-1.11/",
pages = "91--104",
abstract = "Quality estimation (QE), a task of evaluating the quality of translation automatically without human-translated reference, is one of the important challenges for machine translation (MT). As the QE methods, BLEU score for round-trip translation (RTT) had been considered. However, it was found to be a poor predictor of translation quality since BLEU was not an adequate metric to detect semantic similarity between input and RTT. Recently, the pre-trained language models have made breakthroughs in many NLP tasks by providing semantically meaningful word and sentence embeddings. In this paper, we employ the semantic embeddings to RTT-based QE metric. Our method achieves the highest correlations with human judgments compared to WMT 2019 quality estimation metric task submissions. Additionally, we observe that with semantic-level metrics, RTT-based QE is robust to the choice of a backward translation system and shows consistent performance on both SMT and NMT forward translation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moon-etal-2020-revisiting">
<titleInfo>
<title>Revisiting Round-trip Translation for Quality Estimation</title>
</titleInfo>
<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">Hyunchang</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Park</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 22nd Annual Conference of the European Association for Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Moniz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Fumega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Batista</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Coheur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="family">Parra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Trancoso</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joss</namePart>
<namePart type="family">Moorkens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ana</namePart>
<namePart type="family">Guerberof</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mary</namePart>
<namePart type="family">Nurminen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lena</namePart>
<namePart type="family">Marg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikel</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Forcada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Association for Machine Translation</publisher>
<place>
<placeTerm type="text">Lisboa, Portugal</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Quality estimation (QE), a task of evaluating the quality of translation automatically without human-translated reference, is one of the important challenges for machine translation (MT). As the QE methods, BLEU score for round-trip translation (RTT) had been considered. However, it was found to be a poor predictor of translation quality since BLEU was not an adequate metric to detect semantic similarity between input and RTT. Recently, the pre-trained language models have made breakthroughs in many NLP tasks by providing semantically meaningful word and sentence embeddings. In this paper, we employ the semantic embeddings to RTT-based QE metric. Our method achieves the highest correlations with human judgments compared to WMT 2019 quality estimation metric task submissions. Additionally, we observe that with semantic-level metrics, RTT-based QE is robust to the choice of a backward translation system and shows consistent performance on both SMT and NMT forward translation systems.</abstract>
<identifier type="citekey">moon-etal-2020-revisiting</identifier>
<location>
<url>http://aclanthology.org/2020.eamt-1.11/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>91</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Round-trip Translation for Quality Estimation
%A Moon, Jihyung
%A Cho, Hyunchang
%A Park, Eunjeong L.
%Y Martins, André
%Y Moniz, Helena
%Y Fumega, Sara
%Y Martins, Bruno
%Y Batista, Fernando
%Y Coheur, Luisa
%Y Parra, Carla
%Y Trancoso, Isabel
%Y Turchi, Marco
%Y Bisazza, Arianna
%Y Moorkens, Joss
%Y Guerberof, Ana
%Y Nurminen, Mary
%Y Marg, Lena
%Y Forcada, Mikel L.
%S Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
%D 2020
%8 November
%I European Association for Machine Translation
%C Lisboa, Portugal
%F moon-etal-2020-revisiting
%X Quality estimation (QE), a task of evaluating the quality of translation automatically without human-translated reference, is one of the important challenges for machine translation (MT). As the QE methods, BLEU score for round-trip translation (RTT) had been considered. However, it was found to be a poor predictor of translation quality since BLEU was not an adequate metric to detect semantic similarity between input and RTT. Recently, the pre-trained language models have made breakthroughs in many NLP tasks by providing semantically meaningful word and sentence embeddings. In this paper, we employ the semantic embeddings to RTT-based QE metric. Our method achieves the highest correlations with human judgments compared to WMT 2019 quality estimation metric task submissions. Additionally, we observe that with semantic-level metrics, RTT-based QE is robust to the choice of a backward translation system and shows consistent performance on both SMT and NMT forward translation systems.
%U http://aclanthology.org/2020.eamt-1.11/
%P 91-104
Markdown (Informal)
[Revisiting Round-trip Translation for Quality Estimation](http://aclanthology.org/2020.eamt-1.11/) (Moon et al., EAMT 2020)
ACL
- Jihyung Moon, Hyunchang Cho, and Eunjeong L. Park. 2020. Revisiting Round-trip Translation for Quality Estimation. In Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, pages 91–104, Lisboa, Portugal. European Association for Machine Translation.