@inproceedings{wang-neubig-2019-target,
title = "Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation",
author = "Wang, Xinyi 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/P19-1583",
doi = "10.18653/v1/P19-1583",
pages = "5823--5828",
abstract = "To improve low-resource Neural Machine Translation (NMT) with multilingual corpus, training on the most related high-resource language only is generally more effective than us- ing all data available (Neubig and Hu, 2018). However, it remains a question whether a smart data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose and efficient algorithm, (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show TCS brings significant gains of up to 2 BLEU improvements on three of four languages we test, with minimal training overhead.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-neubig-2019-target">
<titleInfo>
<title>Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Wang</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>To improve low-resource Neural Machine Translation (NMT) with multilingual corpus, training on the most related high-resource language only is generally more effective than us- ing all data available (Neubig and Hu, 2018). However, it remains a question whether a smart data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose and efficient algorithm, (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show TCS brings significant gains of up to 2 BLEU improvements on three of four languages we test, with minimal training overhead.</abstract>
<identifier type="citekey">wang-neubig-2019-target</identifier>
<identifier type="doi">10.18653/v1/P19-1583</identifier>
<location>
<url>https://aclanthology.org/P19-1583</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5823</start>
<end>5828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
%A Wang, Xinyi
%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 wang-neubig-2019-target
%X To improve low-resource Neural Machine Translation (NMT) with multilingual corpus, training on the most related high-resource language only is generally more effective than us- ing all data available (Neubig and Hu, 2018). However, it remains a question whether a smart data selection strategy can further improve low-resource NMT with data from other auxiliary languages. In this paper, we seek to construct a sampling distribution over all multilingual data, so that it minimizes the training loss of the low-resource language. Based on this formulation, we propose and efficient algorithm, (TCS), which first samples a target sentence, and then conditionally samples its source sentence. Experiments show TCS brings significant gains of up to 2 BLEU improvements on three of four languages we test, with minimal training overhead.
%R 10.18653/v1/P19-1583
%U https://aclanthology.org/P19-1583
%U https://doi.org/10.18653/v1/P19-1583
%P 5823-5828
Markdown (Informal)
[Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation](https://aclanthology.org/P19-1583) (Wang & Neubig, ACL 2019)
ACL