<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="son-lyu-2020-sparse">
    <titleInfo>
        <title>Sparse and Decorrelated Representations for Stable Zero-shot NMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Bokyung</namePart>
        <namePart type="family">Son</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sungwon</namePart>
        <namePart type="family">Lyu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yulan</namePart>
            <namePart type="family">He</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Using a single encoder and decoder for all directions and training with English-centric data is a popular scheme for multilingual NMT. However, zero-shot translation under this scheme is vulnerable to changes in training conditions, as the model degenerates by decoding non-English texts into English regardless of the target specifier token. We present that enforcing both sparsity and decorrelation on encoder intermediate representations with the SLNI regularizer (Aljundi et al., 2019) efficiently mitigates this problem, without performance loss in supervised directions. Notably, effects of SLNI turns out to be irrelevant to promoting language-invariance in encoder representations.</abstract>
    <identifier type="citekey">son-lyu-2020-sparse</identifier>
    <identifier type="doi">10.18653/v1/2020.findings-emnlp.205</identifier>
    <location>
        <url>https://aclanthology.org/2020.findings-emnlp.205</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>2260</start>
            <end>2266</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sparse and Decorrelated Representations for Stable Zero-shot NMT
%A Son, Bokyung
%A Lyu, Sungwon
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F son-lyu-2020-sparse
%X Using a single encoder and decoder for all directions and training with English-centric data is a popular scheme for multilingual NMT. However, zero-shot translation under this scheme is vulnerable to changes in training conditions, as the model degenerates by decoding non-English texts into English regardless of the target specifier token. We present that enforcing both sparsity and decorrelation on encoder intermediate representations with the SLNI regularizer (Aljundi et al., 2019) efficiently mitigates this problem, without performance loss in supervised directions. Notably, effects of SLNI turns out to be irrelevant to promoting language-invariance in encoder representations.
%R 10.18653/v1/2020.findings-emnlp.205
%U https://aclanthology.org/2020.findings-emnlp.205
%U https://doi.org/10.18653/v1/2020.findings-emnlp.205
%P 2260-2266

Markdown (Informal)

[Sparse and Decorrelated Representations for Stable Zero-shot NMT](https://aclanthology.org/2020.findings-emnlp.205) (Son & Lyu, Findings 2020)

• Sparse and Decorrelated Representations for Stable Zero-shot NMT (Son & Lyu, Findings 2020)

ACL

• Bokyung Son and Sungwon Lyu. 2020. Sparse and Decorrelated Representations for Stable Zero-shot NMT. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2260–2266, Online. Association for Computational Linguistics.