@inproceedings{wang-etal-2024-reducing,
title = "Reducing Redundancy in {J}apanese-to-{E}nglish Translation: A Multi-Pipeline Approach for Translating Repeated Elements in {J}apanese",
author = "Wang, Qiao and
Huang, Yixuan and
Yuan, Zheng",
editor = "Haddow, Barry and
Kocmi, Tom and
Koehn, Philipp and
Monz, Christof",
booktitle = "Proceedings of the Ninth Conference on Machine Translation",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.wmt-1.107",
pages = "1047--1055",
abstract = "This paper presents a multi-pipeline Japanese-to-English machine translation (MT) system designed to address the challenge of translating repeated elements from Japanese into fluent and lexically diverse English. The system is developed as part of the Non-Repetitive Translation Task at WMT24, which focuses on minimizing redundancy while maintaining high translation quality. Our approach utilizes MeCab, the de facto NLP tool for Japanese, for the identification of repeated elements, and Claude Sonnet 3.5, a large language model (LLM), for translation and proofreading. The system effectively accomplishes the shared task by identifying and translating in a diversified manner 89.79{\%} of the 470 repeated instances in the testing dataset, and achieving an average translation quality score of 4.60 out of 5, significantly surpassing the baseline score of 3.88. Analysis also revealed the challenges encountered, particularly in identifying standalone noun-suffix elements and occasional cases of consistent translations or mistranslations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-reducing">
<titleInfo>
<title>Reducing Redundancy in Japanese-to-English Translation: A Multi-Pipeline Approach for Translating Repeated Elements in Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yixuan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth Conference on Machine Translation</title>
</titleInfo>
<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">Philipp</namePart>
<namePart type="family">Koehn</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">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a multi-pipeline Japanese-to-English machine translation (MT) system designed to address the challenge of translating repeated elements from Japanese into fluent and lexically diverse English. The system is developed as part of the Non-Repetitive Translation Task at WMT24, which focuses on minimizing redundancy while maintaining high translation quality. Our approach utilizes MeCab, the de facto NLP tool for Japanese, for the identification of repeated elements, and Claude Sonnet 3.5, a large language model (LLM), for translation and proofreading. The system effectively accomplishes the shared task by identifying and translating in a diversified manner 89.79% of the 470 repeated instances in the testing dataset, and achieving an average translation quality score of 4.60 out of 5, significantly surpassing the baseline score of 3.88. Analysis also revealed the challenges encountered, particularly in identifying standalone noun-suffix elements and occasional cases of consistent translations or mistranslations.</abstract>
<identifier type="citekey">wang-etal-2024-reducing</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.107</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1047</start>
<end>1055</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reducing Redundancy in Japanese-to-English Translation: A Multi-Pipeline Approach for Translating Repeated Elements in Japanese
%A Wang, Qiao
%A Huang, Yixuan
%A Yuan, Zheng
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Koehn, Philipp
%Y Monz, Christof
%S Proceedings of the Ninth Conference on Machine Translation
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F wang-etal-2024-reducing
%X This paper presents a multi-pipeline Japanese-to-English machine translation (MT) system designed to address the challenge of translating repeated elements from Japanese into fluent and lexically diverse English. The system is developed as part of the Non-Repetitive Translation Task at WMT24, which focuses on minimizing redundancy while maintaining high translation quality. Our approach utilizes MeCab, the de facto NLP tool for Japanese, for the identification of repeated elements, and Claude Sonnet 3.5, a large language model (LLM), for translation and proofreading. The system effectively accomplishes the shared task by identifying and translating in a diversified manner 89.79% of the 470 repeated instances in the testing dataset, and achieving an average translation quality score of 4.60 out of 5, significantly surpassing the baseline score of 3.88. Analysis also revealed the challenges encountered, particularly in identifying standalone noun-suffix elements and occasional cases of consistent translations or mistranslations.
%U https://aclanthology.org/2024.wmt-1.107
%P 1047-1055
Markdown (Informal)
[Reducing Redundancy in Japanese-to-English Translation: A Multi-Pipeline Approach for Translating Repeated Elements in Japanese](https://aclanthology.org/2024.wmt-1.107) (Wang et al., WMT 2024)
ACL