@inproceedings{shi-2025-data,
title = "Data Augmentation for Low-resource Neural Machine Translation: A Systematic Analysis",
author = "Shi, Zhiqiang",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.30/",
pages = "510--522",
ISBN = "979-8-89176-303-6",
abstract = "As an effective way to address data scarcity problem, data augmentation has received significant interest in low-resource neural machine translation, while the latter has the potential to reduce digital divide and benefit out of domain translation. However, the existing works mainly focus on how to generate the synthetic data, while the synthetic data quality and the way we use the synthetic data also matter. In this paper, we give a systematic analysis of data augmentation for low-resource neural machine translation that encompasses all the three aspects. We show that with careful control of the synthetic data quality and the way we use the synthetic data, the performance can be greatly boosted even with the same method to generate the synthetic data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-2025-data">
<titleInfo>
<title>Data Augmentation for Low-resource Neural Machine Translation: A Systematic Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhiqiang</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</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">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>As an effective way to address data scarcity problem, data augmentation has received significant interest in low-resource neural machine translation, while the latter has the potential to reduce digital divide and benefit out of domain translation. However, the existing works mainly focus on how to generate the synthetic data, while the synthetic data quality and the way we use the synthetic data also matter. In this paper, we give a systematic analysis of data augmentation for low-resource neural machine translation that encompasses all the three aspects. We show that with careful control of the synthetic data quality and the way we use the synthetic data, the performance can be greatly boosted even with the same method to generate the synthetic data.</abstract>
<identifier type="citekey">shi-2025-data</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.30/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>510</start>
<end>522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation for Low-resource Neural Machine Translation: A Systematic Analysis
%A Shi, Zhiqiang
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F shi-2025-data
%X As an effective way to address data scarcity problem, data augmentation has received significant interest in low-resource neural machine translation, while the latter has the potential to reduce digital divide and benefit out of domain translation. However, the existing works mainly focus on how to generate the synthetic data, while the synthetic data quality and the way we use the synthetic data also matter. In this paper, we give a systematic analysis of data augmentation for low-resource neural machine translation that encompasses all the three aspects. We show that with careful control of the synthetic data quality and the way we use the synthetic data, the performance can be greatly boosted even with the same method to generate the synthetic data.
%U https://aclanthology.org/2025.findings-ijcnlp.30/
%P 510-522
Markdown (Informal)
[Data Augmentation for Low-resource Neural Machine Translation: A Systematic Analysis](https://aclanthology.org/2025.findings-ijcnlp.30/) (Shi, Findings 2025)
ACL
- Zhiqiang Shi. 2025. Data Augmentation for Low-resource Neural Machine Translation: A Systematic Analysis. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 510–522, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.