@inproceedings{przystupa-abdul-mageed-2019-neural,
title = "Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation",
author = "Przystupa, Michael and
Abdul-Mageed, Muhammad",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5431",
doi = "10.18653/v1/W19-5431",
pages = "224--235",
abstract = "We present our contribution to the WMT19 Similar Language Translation shared task. We investigate the utility of neural machine translation on three low-resource, similar language pairs: Spanish {--} Portuguese, Czech {--} Polish, and Hindi {--} Nepali. Since state-of-the-art neural machine translation systems still require large amounts of bitext, which we do not have for the pairs we consider, we focus primarily on incorporating monolingual data into our models with backtranslation. In our analysis, we found Transformer models to work best on Spanish {--} Portuguese and Czech {--} Polish translation, whereas LSTMs with global attention worked best on Hindi {--} Nepali translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="przystupa-abdul-mageed-2019-neural">
<titleInfo>
<title>Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Przystupa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our contribution to the WMT19 Similar Language Translation shared task. We investigate the utility of neural machine translation on three low-resource, similar language pairs: Spanish – Portuguese, Czech – Polish, and Hindi – Nepali. Since state-of-the-art neural machine translation systems still require large amounts of bitext, which we do not have for the pairs we consider, we focus primarily on incorporating monolingual data into our models with backtranslation. In our analysis, we found Transformer models to work best on Spanish – Portuguese and Czech – Polish translation, whereas LSTMs with global attention worked best on Hindi – Nepali translation.</abstract>
<identifier type="citekey">przystupa-abdul-mageed-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-5431</identifier>
<location>
<url>https://aclanthology.org/W19-5431</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>224</start>
<end>235</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation
%A Przystupa, Michael
%A Abdul-Mageed, Muhammad
%S Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F przystupa-abdul-mageed-2019-neural
%X We present our contribution to the WMT19 Similar Language Translation shared task. We investigate the utility of neural machine translation on three low-resource, similar language pairs: Spanish – Portuguese, Czech – Polish, and Hindi – Nepali. Since state-of-the-art neural machine translation systems still require large amounts of bitext, which we do not have for the pairs we consider, we focus primarily on incorporating monolingual data into our models with backtranslation. In our analysis, we found Transformer models to work best on Spanish – Portuguese and Czech – Polish translation, whereas LSTMs with global attention worked best on Hindi – Nepali translation.
%R 10.18653/v1/W19-5431
%U https://aclanthology.org/W19-5431
%U https://doi.org/10.18653/v1/W19-5431
%P 224-235
Markdown (Informal)
[Neural Machine Translation of Low-Resource and Similar Languages with Backtranslation](https://aclanthology.org/W19-5431) (Przystupa & Abdul-Mageed, 2019)
ACL