@inproceedings{song-etal-2021-sentsim,
title = "{S}ent{S}im: Crosslingual Semantic Evaluation of Machine Translation",
author = "Song, Yurun and
Zhao, Junchen and
Specia, Lucia",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.252/",
doi = "10.18653/v1/2021.naacl-main.252",
pages = "3143--3156",
abstract = "Machine translation (MT) is currently evaluated in one of two ways: in a monolingual fashion, by comparison with the system output to one or more human reference translations, or in a trained crosslingual fashion, by building a supervised model to predict quality scores from human-labeled data. In this paper, we propose a more cost-effective, yet well performing unsupervised alternative SentSim: relying on strong pretrained multilingual word and sentence representations, we directly compare the source with the machine translated sentence, thus avoiding the need for both reference translations and labelled training data. The metric builds on state-of-the-art embedding-based approaches {--} namely BERTScore and Word Mover`s Distance {--} by incorporating a notion of sentence semantic similarity. By doing so, it achieves better correlation with human scores on different datasets. We show that it outperforms these and other metrics in the standard monolingual setting (MT-reference translation), a well as in the source-MT bilingual setting, where it performs on par with glass-box approaches to quality estimation that rely on MT model information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2021-sentsim">
<titleInfo>
<title>SentSim: Crosslingual Semantic Evaluation of Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yurun</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junchen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Machine translation (MT) is currently evaluated in one of two ways: in a monolingual fashion, by comparison with the system output to one or more human reference translations, or in a trained crosslingual fashion, by building a supervised model to predict quality scores from human-labeled data. In this paper, we propose a more cost-effective, yet well performing unsupervised alternative SentSim: relying on strong pretrained multilingual word and sentence representations, we directly compare the source with the machine translated sentence, thus avoiding the need for both reference translations and labelled training data. The metric builds on state-of-the-art embedding-based approaches – namely BERTScore and Word Mover‘s Distance – by incorporating a notion of sentence semantic similarity. By doing so, it achieves better correlation with human scores on different datasets. We show that it outperforms these and other metrics in the standard monolingual setting (MT-reference translation), a well as in the source-MT bilingual setting, where it performs on par with glass-box approaches to quality estimation that rely on MT model information.</abstract>
<identifier type="citekey">song-etal-2021-sentsim</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.252</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.252/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3143</start>
<end>3156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SentSim: Crosslingual Semantic Evaluation of Machine Translation
%A Song, Yurun
%A Zhao, Junchen
%A Specia, Lucia
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F song-etal-2021-sentsim
%X Machine translation (MT) is currently evaluated in one of two ways: in a monolingual fashion, by comparison with the system output to one or more human reference translations, or in a trained crosslingual fashion, by building a supervised model to predict quality scores from human-labeled data. In this paper, we propose a more cost-effective, yet well performing unsupervised alternative SentSim: relying on strong pretrained multilingual word and sentence representations, we directly compare the source with the machine translated sentence, thus avoiding the need for both reference translations and labelled training data. The metric builds on state-of-the-art embedding-based approaches – namely BERTScore and Word Mover‘s Distance – by incorporating a notion of sentence semantic similarity. By doing so, it achieves better correlation with human scores on different datasets. We show that it outperforms these and other metrics in the standard monolingual setting (MT-reference translation), a well as in the source-MT bilingual setting, where it performs on par with glass-box approaches to quality estimation that rely on MT model information.
%R 10.18653/v1/2021.naacl-main.252
%U https://aclanthology.org/2021.naacl-main.252/
%U https://doi.org/10.18653/v1/2021.naacl-main.252
%P 3143-3156
Markdown (Informal)
[SentSim: Crosslingual Semantic Evaluation of Machine Translation](https://aclanthology.org/2021.naacl-main.252/) (Song et al., NAACL 2021)
ACL
- Yurun Song, Junchen Zhao, and Lucia Specia. 2021. SentSim: Crosslingual Semantic Evaluation of Machine Translation. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3143–3156, Online. Association for Computational Linguistics.