<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2020-context">
    <titleInfo>
        <title>Context-Aware Cross-Attention for Non-Autoregressive Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Liang</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Longyue</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Di</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dacheng</namePart>
        <namePart type="family">Tao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhaopeng</namePart>
        <namePart type="family">Tu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 28th International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Donia</namePart>
            <namePart type="family">Scott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nuria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Chengqing</namePart>
            <namePart type="family">Zong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence. However, due to the lack of target dependency modelling in the decoder, the conditional generation process heavily depends on the cross-attention. In this paper, we reveal a localness perception problem in NAT cross-attention, for which it is difficult to adequately capture source context. To alleviate this problem, we propose to enhance signals of neighbour source tokens into conventional cross-attention. Experimental results on several representative datasets show that our approach can consistently improve translation quality over strong NAT baselines. Extensive analyses demonstrate that the enhanced cross-attention achieves better exploitation of source contexts by leveraging both local and global information.</abstract>
    <identifier type="citekey">ding-etal-2020-context</identifier>
    <identifier type="doi">10.18653/v1/2020.coling-main.389</identifier>
    <location>
        <url>https://aclanthology.org/2020.coling-main.389</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>4396</start>
            <end>4402</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Context-Aware Cross-Attention for Non-Autoregressive Translation
%A Ding, Liang
%A Wang, Longyue
%A Wu, Di
%A Tao, Dacheng
%A Tu, Zhaopeng
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F ding-etal-2020-context
%X Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence. However, due to the lack of target dependency modelling in the decoder, the conditional generation process heavily depends on the cross-attention. In this paper, we reveal a localness perception problem in NAT cross-attention, for which it is difficult to adequately capture source context. To alleviate this problem, we propose to enhance signals of neighbour source tokens into conventional cross-attention. Experimental results on several representative datasets show that our approach can consistently improve translation quality over strong NAT baselines. Extensive analyses demonstrate that the enhanced cross-attention achieves better exploitation of source contexts by leveraging both local and global information.
%R 10.18653/v1/2020.coling-main.389
%U https://aclanthology.org/2020.coling-main.389
%U https://doi.org/10.18653/v1/2020.coling-main.389
%P 4396-4402

Markdown (Informal)

[Context-Aware Cross-Attention for Non-Autoregressive Translation](https://aclanthology.org/2020.coling-main.389) (Ding et al., COLING 2020)

• Context-Aware Cross-Attention for Non-Autoregressive Translation (Ding et al., COLING 2020)

ACL

• Liang Ding, Longyue Wang, Di Wu, Dacheng Tao, and Zhaopeng Tu. 2020. Context-Aware Cross-Attention for Non-Autoregressive Translation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4396–4402, Barcelona, Spain (Online). International Committee on Computational Linguistics.