@inproceedings{li-etal-2025-enhancing-large,
title = "Enhancing Large Language Models for Document-Level Translation Post-Editing Using Monolingual Data",
author = "Li, Zongyao and
Rao, Zhiqiang and
Shang, Hengchao and
Guo, Jiaxin and
Li, Shaojun and
Wei, Daimeng and
Yang, Hao",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.591/",
pages = "8830--8840",
abstract = "The translation capabilities of neural machine translation (NMT) models based on the encoder-decoder framework are extremely potent. Although Large Language Models (LLMs) have achieved remarkable results in many tasks, they have not reached state-of-the-art performance in NMT. However, traditional NMT still faces significant challenges in areas of document translation such as context consistency, tense, and pronoun resolution, where LLMs inherently possess substantial advantages. Instead of directly using LLMs for translation, employing them for Automatic Post-Editing (APE) to post-edit NMT outputs proves to be a viable option. However, document-level bilingual data is extremely scarce. This paper proposes a method that can effectively leverage the capabilities of LLMs to optimize document translation using only monolingual data. By employing two NMT models in opposite directions (Source-to-Target and Target-to-Source), we generate pseudo-document training data for the training of APE. We have identified and resolved the issue between training and inference mode inconsistency brought about by the pseudo-document training data. The final experimental results demonstrate that by using only document-level monolingual data, we can significantly improve the quality of NMT and greatly enhance issues such as reference and contextual consistency in NMT."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-enhancing-large">
<titleInfo>
<title>Enhancing Large Language Models for Document-Level Translation Post-Editing Using Monolingual Data</title>
</titleInfo>
<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">Zhiqiang</namePart>
<namePart type="family">Rao</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">Jiaxin</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaojun</namePart>
<namePart type="family">Li</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">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The translation capabilities of neural machine translation (NMT) models based on the encoder-decoder framework are extremely potent. Although Large Language Models (LLMs) have achieved remarkable results in many tasks, they have not reached state-of-the-art performance in NMT. However, traditional NMT still faces significant challenges in areas of document translation such as context consistency, tense, and pronoun resolution, where LLMs inherently possess substantial advantages. Instead of directly using LLMs for translation, employing them for Automatic Post-Editing (APE) to post-edit NMT outputs proves to be a viable option. However, document-level bilingual data is extremely scarce. This paper proposes a method that can effectively leverage the capabilities of LLMs to optimize document translation using only monolingual data. By employing two NMT models in opposite directions (Source-to-Target and Target-to-Source), we generate pseudo-document training data for the training of APE. We have identified and resolved the issue between training and inference mode inconsistency brought about by the pseudo-document training data. The final experimental results demonstrate that by using only document-level monolingual data, we can significantly improve the quality of NMT and greatly enhance issues such as reference and contextual consistency in NMT.</abstract>
<identifier type="citekey">li-etal-2025-enhancing-large</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.591/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>8830</start>
<end>8840</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Large Language Models for Document-Level Translation Post-Editing Using Monolingual Data
%A Li, Zongyao
%A Rao, Zhiqiang
%A Shang, Hengchao
%A Guo, Jiaxin
%A Li, Shaojun
%A Wei, Daimeng
%A Yang, Hao
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F li-etal-2025-enhancing-large
%X The translation capabilities of neural machine translation (NMT) models based on the encoder-decoder framework are extremely potent. Although Large Language Models (LLMs) have achieved remarkable results in many tasks, they have not reached state-of-the-art performance in NMT. However, traditional NMT still faces significant challenges in areas of document translation such as context consistency, tense, and pronoun resolution, where LLMs inherently possess substantial advantages. Instead of directly using LLMs for translation, employing them for Automatic Post-Editing (APE) to post-edit NMT outputs proves to be a viable option. However, document-level bilingual data is extremely scarce. This paper proposes a method that can effectively leverage the capabilities of LLMs to optimize document translation using only monolingual data. By employing two NMT models in opposite directions (Source-to-Target and Target-to-Source), we generate pseudo-document training data for the training of APE. We have identified and resolved the issue between training and inference mode inconsistency brought about by the pseudo-document training data. The final experimental results demonstrate that by using only document-level monolingual data, we can significantly improve the quality of NMT and greatly enhance issues such as reference and contextual consistency in NMT.
%U https://aclanthology.org/2025.coling-main.591/
%P 8830-8840
Markdown (Informal)
[Enhancing Large Language Models for Document-Level Translation Post-Editing Using Monolingual Data](https://aclanthology.org/2025.coling-main.591/) (Li et al., COLING 2025)
ACL