@inproceedings{jung-etal-2024-towards,
title = "Towards Precise Localization of Critical Errors in Machine Translation",
author = "Jung, Dahyun and
Eo, Sugyeong and
Lim, Heuiseok",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.177",
doi = "10.18653/v1/2024.findings-acl.177",
pages = "3000--3012",
abstract = "The advent of large language models has experienced a remarkable improvement in the field of machine translation. However, machine translation is still vulnerable to critical meaning deviations, which may incur catastrophic issues in social or ethical contexts. In particular, existing critical error detection primarily focuses on identifying sentence-level errors, leaving the precise localization of such errors within the sentence unaddressed. In this paper, we introduce a new task, word-level critical error detection (WCED), to detect critical errors at a fine-grained level in machine translation sentences. The task aims to identify the parts of a machine translation that contain catastrophic meaning distortions. We hypothesize that the ability to determine errors at the sentence level will positively influence the detection of more granular errors. We propose a sentence-level error detection module to predict which words in a sentence have critical errors. Experimental results demonstrate that our method outperforms existing methodologies and LLM in En-De, Zh-En, En-Ru, and En-Ko. Our method is helpful for determining the fine-grained location of errors. We hope that such studies will improve the capacity to address critical errors adeptly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jung-etal-2024-towards">
<titleInfo>
<title>Towards Precise Localization of Critical Errors in Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dahyun</namePart>
<namePart type="family">Jung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sugyeong</namePart>
<namePart type="family">Eo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</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>Findings of the Association for Computational Linguistics: ACL 2024</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>The advent of large language models has experienced a remarkable improvement in the field of machine translation. However, machine translation is still vulnerable to critical meaning deviations, which may incur catastrophic issues in social or ethical contexts. In particular, existing critical error detection primarily focuses on identifying sentence-level errors, leaving the precise localization of such errors within the sentence unaddressed. In this paper, we introduce a new task, word-level critical error detection (WCED), to detect critical errors at a fine-grained level in machine translation sentences. The task aims to identify the parts of a machine translation that contain catastrophic meaning distortions. We hypothesize that the ability to determine errors at the sentence level will positively influence the detection of more granular errors. We propose a sentence-level error detection module to predict which words in a sentence have critical errors. Experimental results demonstrate that our method outperforms existing methodologies and LLM in En-De, Zh-En, En-Ru, and En-Ko. Our method is helpful for determining the fine-grained location of errors. We hope that such studies will improve the capacity to address critical errors adeptly.</abstract>
<identifier type="citekey">jung-etal-2024-towards</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.177</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.177</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>3000</start>
<end>3012</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Precise Localization of Critical Errors in Machine Translation
%A Jung, Dahyun
%A Eo, Sugyeong
%A Lim, Heuiseok
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F jung-etal-2024-towards
%X The advent of large language models has experienced a remarkable improvement in the field of machine translation. However, machine translation is still vulnerable to critical meaning deviations, which may incur catastrophic issues in social or ethical contexts. In particular, existing critical error detection primarily focuses on identifying sentence-level errors, leaving the precise localization of such errors within the sentence unaddressed. In this paper, we introduce a new task, word-level critical error detection (WCED), to detect critical errors at a fine-grained level in machine translation sentences. The task aims to identify the parts of a machine translation that contain catastrophic meaning distortions. We hypothesize that the ability to determine errors at the sentence level will positively influence the detection of more granular errors. We propose a sentence-level error detection module to predict which words in a sentence have critical errors. Experimental results demonstrate that our method outperforms existing methodologies and LLM in En-De, Zh-En, En-Ru, and En-Ko. Our method is helpful for determining the fine-grained location of errors. We hope that such studies will improve the capacity to address critical errors adeptly.
%R 10.18653/v1/2024.findings-acl.177
%U https://aclanthology.org/2024.findings-acl.177
%U https://doi.org/10.18653/v1/2024.findings-acl.177
%P 3000-3012
Markdown (Informal)
[Towards Precise Localization of Critical Errors in Machine Translation](https://aclanthology.org/2024.findings-acl.177) (Jung et al., Findings 2024)
ACL