@inproceedings{lim-etal-2024-simpsons,
title = "Simpson{'}s Paradox and the Accuracy-Fluency Tradeoff in Translation",
author = "Lim, Zheng Wei and
Vylomova, Ekaterina and
Cohn, Trevor and
Kemp, Charles",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-short.9",
doi = "10.18653/v1/2024.acl-short.9",
pages = "92--103",
abstract = "A good translation should be faithful to the source and should respect the norms of the target language. We address a theoretical puzzle about the relationship between these objectives. On one hand, intuition and some prior work suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source can only be achieved at the cost of fluency. On the other hand, quality assessment researchers often suggest that accuracy and fluency are highly correlated and difficult for human raters to distinguish (Callison-Burch et al., 2007). We show that the tension between these views is an instance of Simpson{'}s paradox, and that accuracy and fluency are positively correlated at the level of the corpus but trade off at the level of individual source segments. We further suggest that the relationship between accuracy and fluency is best evaluated at the segment (or sentence) level, and that the trade off between these dimensions has implications both for assessing translation quality and developing improved MT systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2024-simpsons">
<titleInfo>
<title>Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="given">Wei</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charles</namePart>
<namePart type="family">Kemp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A good translation should be faithful to the source and should respect the norms of the target language. We address a theoretical puzzle about the relationship between these objectives. On one hand, intuition and some prior work suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source can only be achieved at the cost of fluency. On the other hand, quality assessment researchers often suggest that accuracy and fluency are highly correlated and difficult for human raters to distinguish (Callison-Burch et al., 2007). We show that the tension between these views is an instance of Simpson’s paradox, and that accuracy and fluency are positively correlated at the level of the corpus but trade off at the level of individual source segments. We further suggest that the relationship between accuracy and fluency is best evaluated at the segment (or sentence) level, and that the trade off between these dimensions has implications both for assessing translation quality and developing improved MT systems.</abstract>
<identifier type="citekey">lim-etal-2024-simpsons</identifier>
<identifier type="doi">10.18653/v1/2024.acl-short.9</identifier>
<location>
<url>https://aclanthology.org/2024.acl-short.9</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>92</start>
<end>103</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation
%A Lim, Zheng Wei
%A Vylomova, Ekaterina
%A Cohn, Trevor
%A Kemp, Charles
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F lim-etal-2024-simpsons
%X A good translation should be faithful to the source and should respect the norms of the target language. We address a theoretical puzzle about the relationship between these objectives. On one hand, intuition and some prior work suggest that accuracy and fluency should trade off against each other, and that capturing every detail of the source can only be achieved at the cost of fluency. On the other hand, quality assessment researchers often suggest that accuracy and fluency are highly correlated and difficult for human raters to distinguish (Callison-Burch et al., 2007). We show that the tension between these views is an instance of Simpson’s paradox, and that accuracy and fluency are positively correlated at the level of the corpus but trade off at the level of individual source segments. We further suggest that the relationship between accuracy and fluency is best evaluated at the segment (or sentence) level, and that the trade off between these dimensions has implications both for assessing translation quality and developing improved MT systems.
%R 10.18653/v1/2024.acl-short.9
%U https://aclanthology.org/2024.acl-short.9
%U https://doi.org/10.18653/v1/2024.acl-short.9
%P 92-103
Markdown (Informal)
[Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation](https://aclanthology.org/2024.acl-short.9) (Lim et al., ACL 2024)
ACL
- Zheng Wei Lim, Ekaterina Vylomova, Trevor Cohn, and Charles Kemp. 2024. Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 92–103, Bangkok, Thailand. Association for Computational Linguistics.