@inproceedings{xia-etal-2019-generalized,
title = "Generalized Data Augmentation for Low-Resource Translation",
author = "Xia, Mengzhou and
Kong, Xiang and
Anastasopoulos, Antonios and
Neubig, Graham",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1579",
doi = "10.18653/v1/P19-1579",
pages = "5786--5796",
abstract = "Low-resource language pairs with a paucity of parallel data pose challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing a large amount of monolingual data is regarded as an effective way to alleviate the problem. In this paper, we propose a general framework of data augmentation for low-resource machine translation not only using target-side monolingual data, but also by pivoting through a related high-resource language. Specifically, we experiment with a two-step pivoting method to convert high-resource data to the low-resource language, making best use of available resources to better approximate the true distribution of the low-resource language. First, we inject low-resource words into high-resource sentences through an induced bilingual dictionary. Second, we further edit the high-resource data injected with low-resource words using a modified unsupervised machine translation framework. Extensive experiments on four low-resource datasets show that under extreme low-resource settings, our data augmentation techniques improve translation quality by up to 1.5 to 8 BLEU points compared to supervised back-translation baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2019-generalized">
<titleInfo>
<title>Generalized Data Augmentation for Low-Resource Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mengzhou</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Low-resource language pairs with a paucity of parallel data pose challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing a large amount of monolingual data is regarded as an effective way to alleviate the problem. In this paper, we propose a general framework of data augmentation for low-resource machine translation not only using target-side monolingual data, but also by pivoting through a related high-resource language. Specifically, we experiment with a two-step pivoting method to convert high-resource data to the low-resource language, making best use of available resources to better approximate the true distribution of the low-resource language. First, we inject low-resource words into high-resource sentences through an induced bilingual dictionary. Second, we further edit the high-resource data injected with low-resource words using a modified unsupervised machine translation framework. Extensive experiments on four low-resource datasets show that under extreme low-resource settings, our data augmentation techniques improve translation quality by up to 1.5 to 8 BLEU points compared to supervised back-translation baselines.</abstract>
<identifier type="citekey">xia-etal-2019-generalized</identifier>
<identifier type="doi">10.18653/v1/P19-1579</identifier>
<location>
<url>https://aclanthology.org/P19-1579</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5786</start>
<end>5796</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalized Data Augmentation for Low-Resource Translation
%A Xia, Mengzhou
%A Kong, Xiang
%A Anastasopoulos, Antonios
%A Neubig, Graham
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F xia-etal-2019-generalized
%X Low-resource language pairs with a paucity of parallel data pose challenges for machine translation in terms of both adequacy and fluency. Data augmentation utilizing a large amount of monolingual data is regarded as an effective way to alleviate the problem. In this paper, we propose a general framework of data augmentation for low-resource machine translation not only using target-side monolingual data, but also by pivoting through a related high-resource language. Specifically, we experiment with a two-step pivoting method to convert high-resource data to the low-resource language, making best use of available resources to better approximate the true distribution of the low-resource language. First, we inject low-resource words into high-resource sentences through an induced bilingual dictionary. Second, we further edit the high-resource data injected with low-resource words using a modified unsupervised machine translation framework. Extensive experiments on four low-resource datasets show that under extreme low-resource settings, our data augmentation techniques improve translation quality by up to 1.5 to 8 BLEU points compared to supervised back-translation baselines.
%R 10.18653/v1/P19-1579
%U https://aclanthology.org/P19-1579
%U https://doi.org/10.18653/v1/P19-1579
%P 5786-5796
Markdown (Informal)
[Generalized Data Augmentation for Low-Resource Translation](https://aclanthology.org/P19-1579) (Xia et al., ACL 2019)
ACL
- Mengzhou Xia, Xiang Kong, Antonios Anastasopoulos, and Graham Neubig. 2019. Generalized Data Augmentation for Low-Resource Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5786–5796, Florence, Italy. Association for Computational Linguistics.