@inproceedings{xu-hong-2022-sub,
title = "Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation",
author = "Xu, Minhan and
Hong, Yu",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.68",
doi = "10.18653/v1/2022.acl-short.68",
pages = "613--619",
abstract = "We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8{\%}, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-hong-2022-sub">
<titleInfo>
<title>Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minhan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.</abstract>
<identifier type="citekey">xu-hong-2022-sub</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.68</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.68</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>613</start>
<end>619</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation
%A Xu, Minhan
%A Hong, Yu
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F xu-hong-2022-sub
%X We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.
%R 10.18653/v1/2022.acl-short.68
%U https://aclanthology.org/2022.acl-short.68
%U https://doi.org/10.18653/v1/2022.acl-short.68
%P 613-619
Markdown (Informal)
[Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation](https://aclanthology.org/2022.acl-short.68) (Xu & Hong, ACL 2022)
ACL