<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bugliarello-okazaki-2020-enhancing">
    <titleInfo>
        <title>Enhancing Machine Translation with Dependency-Aware Self-Attention</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Emanuele</namePart>
        <namePart type="family">Bugliarello</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoaki</namePart>
        <namePart type="family">Okazaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. We show the efficacy of each approach on WMT English-German and English-Turkish, and WAT English-Japanese translation tasks.</abstract>
    <identifier type="citekey">bugliarello-okazaki-2020-enhancing</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.147</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.147</url>
    </location>
    <part>
        <date>2020-jul</date>
        <extent unit="page">
            <start>1618</start>
            <end>1627</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Machine Translation with Dependency-Aware Self-Attention
%A Bugliarello, Emanuele
%A Okazaki, Naoaki
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F bugliarello-okazaki-2020-enhancing
%X Most neural machine translation models only rely on pairs of parallel sentences, assuming syntactic information is automatically learned by an attention mechanism. In this work, we investigate different approaches to incorporate syntactic knowledge in the Transformer model and also propose a novel, parameter-free, dependency-aware self-attention mechanism that improves its translation quality, especially for long sentences and in low-resource scenarios. We show the efficacy of each approach on WMT English-German and English-Turkish, and WAT English-Japanese translation tasks.
%R 10.18653/v1/2020.acl-main.147
%U https://aclanthology.org/2020.acl-main.147
%U https://doi.org/10.18653/v1/2020.acl-main.147
%P 1618-1627

Markdown (Informal)

[Enhancing Machine Translation with Dependency-Aware Self-Attention](https://aclanthology.org/2020.acl-main.147) (Bugliarello & Okazaki, ACL 2020)

• Enhancing Machine Translation with Dependency-Aware Self-Attention (Bugliarello & Okazaki, ACL 2020)

ACL

• Emanuele Bugliarello and Naoaki Okazaki. 2020. Enhancing Machine Translation with Dependency-Aware Self-Attention. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1618–1627, Online. Association for Computational Linguistics.