@inproceedings{sato-etal-2024-tmu,
title = "{TMU}-{HIT}{'}s Submission for the {WMT}24 Quality Estimation Shared Task: Is {GPT}-4 a Good Evaluator for Machine Translation?",
author = "Sato, Ayako and
Nakajima, Kyotaro and
Kim, Hwichan and
Chen, Zhousi and
Komachi, Mamoru",
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-1.38",
doi = "10.18653/v1/2024.wmt-1.38",
pages = "529--534",
abstract = "In machine translation quality estimation (QE), translation quality is evaluated automatically without the need for reference translations. This paper describes our contribution to the sentence-level subtask of Task 1 at the Ninth Machine Translation Conference (WMT24), which predicts quality scores for neural MT outputs without reference translations. We fine-tune GPT-4o mini, a large-scale language model (LLM), with limited data for QE.We report results for the direct assessment (DA) method for four language pairs: English-Gujarati (En-Gu), English-Hindi (En-Hi), English-Tamil (En-Ta), and English-Telugu (En-Te).Experiments under zero-shot, few-shot prompting, and fine-tuning settings revealed significantly low performance in the zero-shot, while fine-tuning achieved accuracy comparable to last year{'}s best scores. Our system demonstrated the effectiveness of this approach in low-resource language QE, securing 1st place in both En-Gu and En-Hi, and 4th place in En-Ta and En-Te.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sato-etal-2024-tmu">
<titleInfo>
<title>TMU-HIT’s Submission for the WMT24 Quality Estimation Shared Task: Is GPT-4 a Good Evaluator for Machine Translation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ayako</namePart>
<namePart type="family">Sato</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyotaro</namePart>
<namePart type="family">Nakajima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hwichan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhousi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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>In machine translation quality estimation (QE), translation quality is evaluated automatically without the need for reference translations. This paper describes our contribution to the sentence-level subtask of Task 1 at the Ninth Machine Translation Conference (WMT24), which predicts quality scores for neural MT outputs without reference translations. We fine-tune GPT-4o mini, a large-scale language model (LLM), with limited data for QE.We report results for the direct assessment (DA) method for four language pairs: English-Gujarati (En-Gu), English-Hindi (En-Hi), English-Tamil (En-Ta), and English-Telugu (En-Te).Experiments under zero-shot, few-shot prompting, and fine-tuning settings revealed significantly low performance in the zero-shot, while fine-tuning achieved accuracy comparable to last year’s best scores. Our system demonstrated the effectiveness of this approach in low-resource language QE, securing 1st place in both En-Gu and En-Hi, and 4th place in En-Ta and En-Te.</abstract>
<identifier type="citekey">sato-etal-2024-tmu</identifier>
<identifier type="doi">10.18653/v1/2024.wmt-1.38</identifier>
<location>
<url>https://aclanthology.org/2024.wmt-1.38</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>529</start>
<end>534</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TMU-HIT’s Submission for the WMT24 Quality Estimation Shared Task: Is GPT-4 a Good Evaluator for Machine Translation?
%A Sato, Ayako
%A Nakajima, Kyotaro
%A Kim, Hwichan
%A Chen, Zhousi
%A Komachi, Mamoru
%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 sato-etal-2024-tmu
%X In machine translation quality estimation (QE), translation quality is evaluated automatically without the need for reference translations. This paper describes our contribution to the sentence-level subtask of Task 1 at the Ninth Machine Translation Conference (WMT24), which predicts quality scores for neural MT outputs without reference translations. We fine-tune GPT-4o mini, a large-scale language model (LLM), with limited data for QE.We report results for the direct assessment (DA) method for four language pairs: English-Gujarati (En-Gu), English-Hindi (En-Hi), English-Tamil (En-Ta), and English-Telugu (En-Te).Experiments under zero-shot, few-shot prompting, and fine-tuning settings revealed significantly low performance in the zero-shot, while fine-tuning achieved accuracy comparable to last year’s best scores. Our system demonstrated the effectiveness of this approach in low-resource language QE, securing 1st place in both En-Gu and En-Hi, and 4th place in En-Ta and En-Te.
%R 10.18653/v1/2024.wmt-1.38
%U https://aclanthology.org/2024.wmt-1.38
%U https://doi.org/10.18653/v1/2024.wmt-1.38
%P 529-534
Markdown (Informal)
[TMU-HIT’s Submission for the WMT24 Quality Estimation Shared Task: Is GPT-4 a Good Evaluator for Machine Translation?](https://aclanthology.org/2024.wmt-1.38) (Sato et al., WMT 2024)
ACL