<?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)

• Parameter Sharing Methods for Multilingual Self-Attentional Translation Models (Sachan & Neubig, 2018)

ACL

• Devendra Sachan and Graham Neubig. 2018. Parameter Sharing Methods for Multilingual Self-Attentional Translation Models. In Proceedings of the Third Conference on Machine Translation: Research Papers, pages 261–271, Brussels, Belgium. Association for Computational Linguistics.