<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-feng-2021-modeling-concentrated">
    <titleInfo>
        <title>Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shaolei</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods. However, dot-product attention only considers the pair-wise correlation between words, resulting in dispersion when dealing with long sentences and neglect of source neighboring relationships. Inspired by linguistics, the above issues are caused by ignoring a type of cross-attention, called concentrated attention, which focuses on several central words and then spreads around them. In this work, we apply Gaussian Mixture Model (GMM) to model the concentrated attention in cross-attention. Experiments and analyses we conducted on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation.</abstract>
    <identifier type="citekey">zhang-feng-2021-modeling-concentrated</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.121</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.121</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>1401</start>
            <end>1411</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model
%A Zhang, Shaolei
%A Feng, Yang
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F zhang-feng-2021-modeling-concentrated
%X Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods. However, dot-product attention only considers the pair-wise correlation between words, resulting in dispersion when dealing with long sentences and neglect of source neighboring relationships. Inspired by linguistics, the above issues are caused by ignoring a type of cross-attention, called concentrated attention, which focuses on several central words and then spreads around them. In this work, we apply Gaussian Mixture Model (GMM) to model the concentrated attention in cross-attention. Experiments and analyses we conducted on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation.
%R 10.18653/v1/2021.findings-emnlp.121
%U https://aclanthology.org/2021.findings-emnlp.121
%U https://doi.org/10.18653/v1/2021.findings-emnlp.121
%P 1401-1411

Markdown (Informal)

[Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model](https://aclanthology.org/2021.findings-emnlp.121) (Zhang & Feng, Findings 2021)

• Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model (Zhang & Feng, Findings 2021)

ACL

• Shaolei Zhang and Yang Feng. 2021. Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1401–1411, Punta Cana, Dominican Republic. Association for Computational Linguistics.