@inproceedings{sennrich-zhang-2019-revisiting,
title = "Revisiting Low-Resource Neural Machine Translation: A Case Study",
author = "Sennrich, Rico and
Zhang, Biao",
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/P19-1021",
doi = "10.18653/v1/P19-1021",
pages = "211--221",
abstract = "It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German{--}English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean{--}English dataset, surpassing previously reported results by 4 BLEU.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sennrich-zhang-2019-revisiting">
<titleInfo>
<title>Revisiting Low-Resource Neural Machine Translation: A Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rico</namePart>
<namePart type="family">Sennrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biao</namePart>
<namePart type="family">Zhang</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>It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German–English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean–English dataset, surpassing previously reported results by 4 BLEU.</abstract>
<identifier type="citekey">sennrich-zhang-2019-revisiting</identifier>
<identifier type="doi">10.18653/v1/P19-1021</identifier>
<location>
<url>https://aclanthology.org/P19-1021</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>211</start>
<end>221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Low-Resource Neural Machine Translation: A Case Study
%A Sennrich, Rico
%A Zhang, Biao
%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 sennrich-zhang-2019-revisiting
%X It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German–English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean–English dataset, surpassing previously reported results by 4 BLEU.
%R 10.18653/v1/P19-1021
%U https://aclanthology.org/P19-1021
%U https://doi.org/10.18653/v1/P19-1021
%P 211-221
Markdown (Informal)
[Revisiting Low-Resource Neural Machine Translation: A Case Study](https://aclanthology.org/P19-1021) (Sennrich & Zhang, ACL 2019)
ACL