@inproceedings{chen-etal-2023-multifaceted,
title = "Multifaceted Challenge Set for Evaluating Machine Translation Performance",
author = "Chen, Xiaoyu and
Wei, Daimeng and
Wu, Zhanglin and
Zhu, Ting and
Shang, Hengchao and
Li, Zongyao and
Guo, Jiaxin and
Xie, Ning and
Lei, Lizhi and
Yang, Hao and
Jiang, Yanfei",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.22",
doi = "10.18653/v1/2023.wmt-1.22",
pages = "217--223",
abstract = "Machine Translation Evaluation is critical to Machine Translation research, as the evaluation results reflect the effectiveness of training strategies. As a result, a fair and efficient evaluation method is necessary. Many researchers have raised questions about currently available evaluation metrics from various perspectives, and propose suggestions accordingly. However, to our knowledge, few researchers has analyzed the difficulty level of source sentence and its influence on evaluation results. This paper presents HW-TSC{'}s submission to the WMT23 MT Test Suites shared task. We propose a systematic approach for construing challenge sets from four aspects: word difficulty, length difficulty, grammar difficulty and model learning difficulty. We open-source two Multifaceted Challenge Sets for Zh→En and En→Zh. We also present results of participants in this year{'}s General MT shared task on our test sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-multifaceted">
<titleInfo>
<title>Multifaceted Challenge Set for Evaluating Machine Translation Performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daimeng</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanglin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengchao</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zongyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizhi</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanfei</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Koehn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barry</namePart>
<namePart type="family">Haddow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Kocmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christof</namePart>
<namePart type="family">Monz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Machine Translation Evaluation is critical to Machine Translation research, as the evaluation results reflect the effectiveness of training strategies. As a result, a fair and efficient evaluation method is necessary. Many researchers have raised questions about currently available evaluation metrics from various perspectives, and propose suggestions accordingly. However, to our knowledge, few researchers has analyzed the difficulty level of source sentence and its influence on evaluation results. This paper presents HW-TSC’s submission to the WMT23 MT Test Suites shared task. We propose a systematic approach for construing challenge sets from four aspects: word difficulty, length difficulty, grammar difficulty and model learning difficulty. We open-source two Multifaceted Challenge Sets for Zh→En and En→Zh. We also present results of participants in this year’s General MT shared task on our test sets.</abstract>
<identifier type="citekey">chen-etal-2023-multifaceted</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.22</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.22</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>217</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multifaceted Challenge Set for Evaluating Machine Translation Performance
%A Chen, Xiaoyu
%A Wei, Daimeng
%A Wu, Zhanglin
%A Zhu, Ting
%A Shang, Hengchao
%A Li, Zongyao
%A Guo, Jiaxin
%A Xie, Ning
%A Lei, Lizhi
%A Yang, Hao
%A Jiang, Yanfei
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-etal-2023-multifaceted
%X Machine Translation Evaluation is critical to Machine Translation research, as the evaluation results reflect the effectiveness of training strategies. As a result, a fair and efficient evaluation method is necessary. Many researchers have raised questions about currently available evaluation metrics from various perspectives, and propose suggestions accordingly. However, to our knowledge, few researchers has analyzed the difficulty level of source sentence and its influence on evaluation results. This paper presents HW-TSC’s submission to the WMT23 MT Test Suites shared task. We propose a systematic approach for construing challenge sets from four aspects: word difficulty, length difficulty, grammar difficulty and model learning difficulty. We open-source two Multifaceted Challenge Sets for Zh→En and En→Zh. We also present results of participants in this year’s General MT shared task on our test sets.
%R 10.18653/v1/2023.wmt-1.22
%U https://aclanthology.org/2023.wmt-1.22
%U https://doi.org/10.18653/v1/2023.wmt-1.22
%P 217-223
Markdown (Informal)
[Multifaceted Challenge Set for Evaluating Machine Translation Performance](https://aclanthology.org/2023.wmt-1.22) (Chen et al., WMT 2023)
ACL
- Xiaoyu Chen, Daimeng Wei, Zhanglin Wu, Ting Zhu, Hengchao Shang, Zongyao Li, Jiaxin Guo, Ning Xie, Lizhi Lei, Hao Yang, and Yanfei Jiang. 2023. Multifaceted Challenge Set for Evaluating Machine Translation Performance. In Proceedings of the Eighth Conference on Machine Translation, pages 217–223, Singapore. Association for Computational Linguistics.