@inproceedings{suen-etal-2024-leveraging,
title = "Leveraging {M}andarin as a Pivot Language for Low-Resource Machine Translation between {C}antonese and {E}nglish",
author = "Suen, King Yiu and
Chow, Rudolf and
Lam, Albert Y.S.",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-1.8/",
doi = "10.18653/v1/2024.loresmt-1.8",
pages = "74--84",
abstract = "Cantonese, the second most prevalent Chinese dialect after Mandarin, has been relatively overlooked in machine translation (MT) due to a scarcity of bilingual resources. In this paper, we propose to leverage Mandarin, a high-resource language, as a pivot language for translating between Cantonese and English. Our method utilizes transfer learning from pre-trained Bidirectional and Auto-Regressive Transformer (BART) models to initialize auxiliary source-pivot and pivot-target MT models. The parameters of the trained auxiliary models are then used to initialize the source-target model. Based on our experiments, our proposed method outperforms several baseline initialization strategies, naive pivot translation, and two commercial translation systems in both translation directions."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suen-etal-2024-leveraging">
<titleInfo>
<title>Leveraging Mandarin as a Pivot Language for Low-Resource Machine Translation between Cantonese and English</title>
</titleInfo>
<name type="personal">
<namePart type="given">King</namePart>
<namePart type="given">Yiu</namePart>
<namePart type="family">Suen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudolf</namePart>
<namePart type="family">Chow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="given">Y.S.</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cantonese, the second most prevalent Chinese dialect after Mandarin, has been relatively overlooked in machine translation (MT) due to a scarcity of bilingual resources. In this paper, we propose to leverage Mandarin, a high-resource language, as a pivot language for translating between Cantonese and English. Our method utilizes transfer learning from pre-trained Bidirectional and Auto-Regressive Transformer (BART) models to initialize auxiliary source-pivot and pivot-target MT models. The parameters of the trained auxiliary models are then used to initialize the source-target model. Based on our experiments, our proposed method outperforms several baseline initialization strategies, naive pivot translation, and two commercial translation systems in both translation directions.</abstract>
<identifier type="citekey">suen-etal-2024-leveraging</identifier>
<identifier type="doi">10.18653/v1/2024.loresmt-1.8</identifier>
<location>
<url>https://aclanthology.org/2024.acl-1.8/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>74</start>
<end>84</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Mandarin as a Pivot Language for Low-Resource Machine Translation between Cantonese and English
%A Suen, King Yiu
%A Chow, Rudolf
%A Lam, Albert Y.S.
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Seventh Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F suen-etal-2024-leveraging
%X Cantonese, the second most prevalent Chinese dialect after Mandarin, has been relatively overlooked in machine translation (MT) due to a scarcity of bilingual resources. In this paper, we propose to leverage Mandarin, a high-resource language, as a pivot language for translating between Cantonese and English. Our method utilizes transfer learning from pre-trained Bidirectional and Auto-Regressive Transformer (BART) models to initialize auxiliary source-pivot and pivot-target MT models. The parameters of the trained auxiliary models are then used to initialize the source-target model. Based on our experiments, our proposed method outperforms several baseline initialization strategies, naive pivot translation, and two commercial translation systems in both translation directions.
%R 10.18653/v1/2024.loresmt-1.8
%U https://aclanthology.org/2024.acl-1.8/
%U https://doi.org/10.18653/v1/2024.loresmt-1.8
%P 74-84
Markdown (Informal)
[Leveraging Mandarin as a Pivot Language for Low-Resource Machine Translation between Cantonese and English](https://aclanthology.org/2024.acl-1.8/) (Suen et al., LoResMT 2024)
ACL