@inproceedings{zhang-2023-iol-research,
title = "{IOL} Research Machine Translation Systems for {WMT}23 Low-Resource {I}ndic Language Translation Shared Task",
author = "Zhang, Wenbo",
editor = "Koehn, Philipp and
Haddow, Barry and
Kocmi, Tom and
Monz, Christof",
booktitle = "Proceedings of the Eighth Conference on Machine Translation",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.wmt-1.94",
doi = "10.18653/v1/2023.wmt-1.94",
pages = "978--982",
abstract = "This paper describes the IOL Research team{'}s submission systems for the WMT23 low-resource Indic language translation shared task. We participated in 4 language pairs, including en-as, en-mz, en-kha, en-mn. We use transformer based neural network architecture to train our machine translation models. Overall, the core of our system is to improve the quality of low resource translation by utilizing monolingual data through pre-training and data augmentation. We first trained two denoising language models similar to T5 and BART using monolingual data, and then used parallel data to fine-tune the pretrained language models to obtain two multilingual machine translation models. The multilingual machine translation models can be used to translate English monolingual data into other multilingual data, forming multilingual parallel data as augmented data. We trained multiple translation models from scratch using augmented data and real parallel data to build the final submission systems by model ensemble. Experimental results show that our method greatly improves the BLEU scores for translation of these four language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-2023-iol-research">
<titleInfo>
<title>IOL Research Machine Translation Systems for WMT23 Low-Resource Indic Language Translation Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth Conference on Machine Translation</title>
</titleInfo>
<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">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">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">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the IOL Research team’s submission systems for the WMT23 low-resource Indic language translation shared task. We participated in 4 language pairs, including en-as, en-mz, en-kha, en-mn. We use transformer based neural network architecture to train our machine translation models. Overall, the core of our system is to improve the quality of low resource translation by utilizing monolingual data through pre-training and data augmentation. We first trained two denoising language models similar to T5 and BART using monolingual data, and then used parallel data to fine-tune the pretrained language models to obtain two multilingual machine translation models. The multilingual machine translation models can be used to translate English monolingual data into other multilingual data, forming multilingual parallel data as augmented data. We trained multiple translation models from scratch using augmented data and real parallel data to build the final submission systems by model ensemble. Experimental results show that our method greatly improves the BLEU scores for translation of these four language pairs.</abstract>
<identifier type="citekey">zhang-2023-iol-research</identifier>
<identifier type="doi">10.18653/v1/2023.wmt-1.94</identifier>
<location>
<url>https://aclanthology.org/2023.wmt-1.94</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>978</start>
<end>982</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IOL Research Machine Translation Systems for WMT23 Low-Resource Indic Language Translation Shared Task
%A Zhang, Wenbo
%Y Koehn, Philipp
%Y Haddow, Barry
%Y Kocmi, Tom
%Y Monz, Christof
%S Proceedings of the Eighth Conference on Machine Translation
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhang-2023-iol-research
%X This paper describes the IOL Research team’s submission systems for the WMT23 low-resource Indic language translation shared task. We participated in 4 language pairs, including en-as, en-mz, en-kha, en-mn. We use transformer based neural network architecture to train our machine translation models. Overall, the core of our system is to improve the quality of low resource translation by utilizing monolingual data through pre-training and data augmentation. We first trained two denoising language models similar to T5 and BART using monolingual data, and then used parallel data to fine-tune the pretrained language models to obtain two multilingual machine translation models. The multilingual machine translation models can be used to translate English monolingual data into other multilingual data, forming multilingual parallel data as augmented data. We trained multiple translation models from scratch using augmented data and real parallel data to build the final submission systems by model ensemble. Experimental results show that our method greatly improves the BLEU scores for translation of these four language pairs.
%R 10.18653/v1/2023.wmt-1.94
%U https://aclanthology.org/2023.wmt-1.94
%U https://doi.org/10.18653/v1/2023.wmt-1.94
%P 978-982
Markdown (Informal)
[IOL Research Machine Translation Systems for WMT23 Low-Resource Indic Language Translation Shared Task](https://aclanthology.org/2023.wmt-1.94) (Zhang, WMT 2023)
ACL