@inproceedings{martinez-matsumoto-2016-improving,
title = "Improving Neural Machine Translation on resource-limited pairs using auxiliary data of a third language",
author = "Martinez, Ander and
Matsumoto, Yuji",
editor = "Green, Spence and
Schwartz, Lane",
booktitle = "Conferences of the Association for Machine Translation in the Americas: MT Researchers' Track",
month = oct # " 28 - " # nov # " 1",
year = "2016",
address = "Austin, TX, USA",
publisher = "The Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2016.amta-researchers.11",
pages = "135--148",
abstract = "In the recent years interest in Deep Neural Networks (DNN) has grown in the field of Natural Language Processing, as new training methods have been proposed. The usage of DNN has achieved state-of-the-art performance in various areas. Neural Machine Translation (NMT) described by Bahdanau et al. (2014) and its successive variations have shown promising results. DNN, however, tend to over-fit on small data-sets, which makes this method impracticable for resource-limited language pairs. This article combines three different ideas (splitting words into smaller units, using an extra dataset of a related language pair and using monolingual data) for improving the performance of NMT models on language pairs with limited data. Our experiments show that, in some cases, our proposed approach to subword-units performs better than BPE (Byte pair encoding) and that auxiliary language-pairs and monolingual data can help improve the performance of languages with limited resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="martinez-matsumoto-2016-improving">
<titleInfo>
<title>Improving Neural Machine Translation on resource-limited pairs using auxiliary data of a third language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ander</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-oct 28 - nov 1</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spence</namePart>
<namePart type="family">Green</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Austin, TX, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the recent years interest in Deep Neural Networks (DNN) has grown in the field of Natural Language Processing, as new training methods have been proposed. The usage of DNN has achieved state-of-the-art performance in various areas. Neural Machine Translation (NMT) described by Bahdanau et al. (2014) and its successive variations have shown promising results. DNN, however, tend to over-fit on small data-sets, which makes this method impracticable for resource-limited language pairs. This article combines three different ideas (splitting words into smaller units, using an extra dataset of a related language pair and using monolingual data) for improving the performance of NMT models on language pairs with limited data. Our experiments show that, in some cases, our proposed approach to subword-units performs better than BPE (Byte pair encoding) and that auxiliary language-pairs and monolingual data can help improve the performance of languages with limited resources.</abstract>
<identifier type="citekey">martinez-matsumoto-2016-improving</identifier>
<location>
<url>https://aclanthology.org/2016.amta-researchers.11</url>
</location>
<part>
<date>2016-oct 28 - nov 1</date>
<extent unit="page">
<start>135</start>
<end>148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Neural Machine Translation on resource-limited pairs using auxiliary data of a third language
%A Martinez, Ander
%A Matsumoto, Yuji
%Y Green, Spence
%Y Schwartz, Lane
%S Conferences of the Association for Machine Translation in the Americas: MT Researchers’ Track
%D 2016
%8 oct 28 nov 1
%I The Association for Machine Translation in the Americas
%C Austin, TX, USA
%F martinez-matsumoto-2016-improving
%X In the recent years interest in Deep Neural Networks (DNN) has grown in the field of Natural Language Processing, as new training methods have been proposed. The usage of DNN has achieved state-of-the-art performance in various areas. Neural Machine Translation (NMT) described by Bahdanau et al. (2014) and its successive variations have shown promising results. DNN, however, tend to over-fit on small data-sets, which makes this method impracticable for resource-limited language pairs. This article combines three different ideas (splitting words into smaller units, using an extra dataset of a related language pair and using monolingual data) for improving the performance of NMT models on language pairs with limited data. Our experiments show that, in some cases, our proposed approach to subword-units performs better than BPE (Byte pair encoding) and that auxiliary language-pairs and monolingual data can help improve the performance of languages with limited resources.
%U https://aclanthology.org/2016.amta-researchers.11
%P 135-148
Markdown (Informal)
[Improving Neural Machine Translation on resource-limited pairs using auxiliary data of a third language](https://aclanthology.org/2016.amta-researchers.11) (Martinez & Matsumoto, AMTA 2016)
ACL