@inproceedings{wu-etal-2023-holistic,
title = "A Holistic Approach to Reference-Free Evaluation of Machine Translation",
author = "Wu, Hanming and
Han, Wenjuan and
Di, Hui and
Chen, Yufeng and
Xu, Jinan",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-short.55",
doi = "10.18653/v1/2023.acl-short.55",
pages = "623--636",
abstract = "Traditional machine translation evaluation relies on reference written by humans. While reference-free evaluation gets rid of the constraints of labor-intensive annotations, which can pivot easily to new domains and is more scalable. In this paper, we propose a reference-free evaluation approach that characterizes evaluation as two aspects: (1) fluency: how well the translated text conforms to normal human language usage; (2) faithfulness: how well the translated text reflects the source data. We further split the faithfulness into word-level and sentence-level. Extensive experiments spanning WMT18/19/21 Metrics segment-level daRR and MQM datasets demonstrate that our proposed reference-free approach, ReFreeEval, outperforms SOTA reference-fee metrics like YiSi-2.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2023-holistic">
<titleInfo>
<title>A Holistic Approach to Reference-Free Evaluation of Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanming</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjuan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Di</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional machine translation evaluation relies on reference written by humans. While reference-free evaluation gets rid of the constraints of labor-intensive annotations, which can pivot easily to new domains and is more scalable. In this paper, we propose a reference-free evaluation approach that characterizes evaluation as two aspects: (1) fluency: how well the translated text conforms to normal human language usage; (2) faithfulness: how well the translated text reflects the source data. We further split the faithfulness into word-level and sentence-level. Extensive experiments spanning WMT18/19/21 Metrics segment-level daRR and MQM datasets demonstrate that our proposed reference-free approach, ReFreeEval, outperforms SOTA reference-fee metrics like YiSi-2.</abstract>
<identifier type="citekey">wu-etal-2023-holistic</identifier>
<identifier type="doi">10.18653/v1/2023.acl-short.55</identifier>
<location>
<url>https://aclanthology.org/2023.acl-short.55</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>623</start>
<end>636</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Holistic Approach to Reference-Free Evaluation of Machine Translation
%A Wu, Hanming
%A Han, Wenjuan
%A Di, Hui
%A Chen, Yufeng
%A Xu, Jinan
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F wu-etal-2023-holistic
%X Traditional machine translation evaluation relies on reference written by humans. While reference-free evaluation gets rid of the constraints of labor-intensive annotations, which can pivot easily to new domains and is more scalable. In this paper, we propose a reference-free evaluation approach that characterizes evaluation as two aspects: (1) fluency: how well the translated text conforms to normal human language usage; (2) faithfulness: how well the translated text reflects the source data. We further split the faithfulness into word-level and sentence-level. Extensive experiments spanning WMT18/19/21 Metrics segment-level daRR and MQM datasets demonstrate that our proposed reference-free approach, ReFreeEval, outperforms SOTA reference-fee metrics like YiSi-2.
%R 10.18653/v1/2023.acl-short.55
%U https://aclanthology.org/2023.acl-short.55
%U https://doi.org/10.18653/v1/2023.acl-short.55
%P 623-636
Markdown (Informal)
[A Holistic Approach to Reference-Free Evaluation of Machine Translation](https://aclanthology.org/2023.acl-short.55) (Wu et al., ACL 2023)
ACL