@inproceedings{zhang-etal-2024-reinforcement-learning,
title = "A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual Data",
author = "Zhang, Hongxiao and
Liu, Mingtong and
Li, Chunyou and
Chen, Yufeng and
Xu, Jinan and
Zhou, Ming",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.132",
pages = "1486--1497",
abstract = "Due to the lack of parallel data, the mainstream fine-tuning-based domain adaptation methods have the overfitting problem in the translation of low-resource domains, and it is difficult for the model to learn the in-domain generalization knowledge. To address the above issue, in this work, we propose a novel Reinforcement Learning Domain Adaptation method for Neural Machine Translation (RLDA-NMT) in the low-resource domain. RLDA-NMT utilizes in-domain source monolingual data to make up for the lack of parallel data, and reinforces domain features learning to make the translation model learn the domain-specific knowledge more fully. Specifically, we first train a ranking-based model with a small-scale in-domain parallel corpus, and then adopt it as the reward model to select higher-quality generated translations for reinforcement when fine-tuning pre-trained NMT model using in-domain source monolingual data. We conduct experiments on Education, Laws, Thesis, and Patent domains of Chinese⇔English translation tasks. Experimental results demonstrate that RLDA-NMT can alleviate overfitting and reinforce the NMT model to learn domain-specific knowledge. Additionally, the results also show that RLDA-NMT and back-translation (BT) are nicely complementary to each other, where combining RLDA-NMT with BT can further improve translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-reinforcement-learning">
<titleInfo>
<title>A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongxiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingtong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyou</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to the lack of parallel data, the mainstream fine-tuning-based domain adaptation methods have the overfitting problem in the translation of low-resource domains, and it is difficult for the model to learn the in-domain generalization knowledge. To address the above issue, in this work, we propose a novel Reinforcement Learning Domain Adaptation method for Neural Machine Translation (RLDA-NMT) in the low-resource domain. RLDA-NMT utilizes in-domain source monolingual data to make up for the lack of parallel data, and reinforces domain features learning to make the translation model learn the domain-specific knowledge more fully. Specifically, we first train a ranking-based model with a small-scale in-domain parallel corpus, and then adopt it as the reward model to select higher-quality generated translations for reinforcement when fine-tuning pre-trained NMT model using in-domain source monolingual data. We conduct experiments on Education, Laws, Thesis, and Patent domains of Chinese⇔English translation tasks. Experimental results demonstrate that RLDA-NMT can alleviate overfitting and reinforce the NMT model to learn domain-specific knowledge. Additionally, the results also show that RLDA-NMT and back-translation (BT) are nicely complementary to each other, where combining RLDA-NMT with BT can further improve translation quality.</abstract>
<identifier type="citekey">zhang-etal-2024-reinforcement-learning</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.132</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>1486</start>
<end>1497</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual Data
%A Zhang, Hongxiao
%A Liu, Mingtong
%A Li, Chunyou
%A Chen, Yufeng
%A Xu, Jinan
%A Zhou, Ming
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F zhang-etal-2024-reinforcement-learning
%X Due to the lack of parallel data, the mainstream fine-tuning-based domain adaptation methods have the overfitting problem in the translation of low-resource domains, and it is difficult for the model to learn the in-domain generalization knowledge. To address the above issue, in this work, we propose a novel Reinforcement Learning Domain Adaptation method for Neural Machine Translation (RLDA-NMT) in the low-resource domain. RLDA-NMT utilizes in-domain source monolingual data to make up for the lack of parallel data, and reinforces domain features learning to make the translation model learn the domain-specific knowledge more fully. Specifically, we first train a ranking-based model with a small-scale in-domain parallel corpus, and then adopt it as the reward model to select higher-quality generated translations for reinforcement when fine-tuning pre-trained NMT model using in-domain source monolingual data. We conduct experiments on Education, Laws, Thesis, and Patent domains of Chinese⇔English translation tasks. Experimental results demonstrate that RLDA-NMT can alleviate overfitting and reinforce the NMT model to learn domain-specific knowledge. Additionally, the results also show that RLDA-NMT and back-translation (BT) are nicely complementary to each other, where combining RLDA-NMT with BT can further improve translation quality.
%U https://aclanthology.org/2024.lrec-main.132
%P 1486-1497
Markdown (Informal)
[A Reinforcement Learning Approach to Improve Low-Resource Machine Translation Leveraging Domain Monolingual Data](https://aclanthology.org/2024.lrec-main.132) (Zhang et al., LREC-COLING 2024)
ACL