@inproceedings{sachan-neubig-2018-parameter,
title = "Parameter Sharing Methods for Multilingual Self-Attentional Translation Models",
author = "Sachan, Devendra and
Neubig, Graham",
booktitle = "Proceedings of the Third Conference on Machine Translation: Research Papers",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6327",
doi = "10.18653/v1/W18-6327",
pages = "261--271",
abstract = "In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained models. However, these improvements are not uniform; often multilingual parameter sharing results in a decrease in accuracy due to translation models not being able to accommodate different languages in their limited parameter space. In this work, we examine parameter sharing techniques that strike a happy medium between full sharing and individual training, specifically focusing on the self-attentional \textit{Transformer} model. We find that the full parameter sharing approach leads to increases in BLEU scores mainly when the target languages are from a similar language family. However, even in the case where target languages are from different families where full parameter sharing leads to a noticeable drop in BLEU scores, our proposed methods for partial sharing of parameters can lead to substantial improvements in translation accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sachan-neubig-2018-parameter">
<titleInfo>
<title>Parameter Sharing Methods for Multilingual Self-Attentional Translation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Devendra</namePart>
<namePart type="family">Sachan</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>2018-oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference on Machine Translation: Research Papers</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained models. However, these improvements are not uniform; often multilingual parameter sharing results in a decrease in accuracy due to translation models not being able to accommodate different languages in their limited parameter space. In this work, we examine parameter sharing techniques that strike a happy medium between full sharing and individual training, specifically focusing on the self-attentional Transformer model. We find that the full parameter sharing approach leads to increases in BLEU scores mainly when the target languages are from a similar language family. However, even in the case where target languages are from different families where full parameter sharing leads to a noticeable drop in BLEU scores, our proposed methods for partial sharing of parameters can lead to substantial improvements in translation accuracy.</abstract>
<identifier type="citekey">sachan-neubig-2018-parameter</identifier>
<identifier type="doi">10.18653/v1/W18-6327</identifier>
<location>
<url>https://aclanthology.org/W18-6327</url>
</location>
<part>
<date>2018-oct</date>
<extent unit="page">
<start>261</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parameter Sharing Methods for Multilingual Self-Attentional Translation Models
%A Sachan, Devendra
%A Neubig, Graham
%S Proceedings of the Third Conference on Machine Translation: Research Papers
%D 2018
%8 oct
%I Association for Computational Linguistics
%C Brussels, Belgium
%F sachan-neubig-2018-parameter
%X In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained models. However, these improvements are not uniform; often multilingual parameter sharing results in a decrease in accuracy due to translation models not being able to accommodate different languages in their limited parameter space. In this work, we examine parameter sharing techniques that strike a happy medium between full sharing and individual training, specifically focusing on the self-attentional Transformer model. We find that the full parameter sharing approach leads to increases in BLEU scores mainly when the target languages are from a similar language family. However, even in the case where target languages are from different families where full parameter sharing leads to a noticeable drop in BLEU scores, our proposed methods for partial sharing of parameters can lead to substantial improvements in translation accuracy.
%R 10.18653/v1/W18-6327
%U https://aclanthology.org/W18-6327
%U https://doi.org/10.18653/v1/W18-6327
%P 261-271
Markdown (Informal)
[Parameter Sharing Methods for Multilingual Self-Attentional Translation Models](https://aclanthology.org/W18-6327) (Sachan & Neubig, 2018)
ACL