<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deguchi-etal-2019-dependency">
    <titleInfo>
        <title>Dependency-Based Self-Attention for Transformer NMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hiroyuki</namePart>
        <namePart type="family">Deguchi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Akihiro</namePart>
        <namePart type="family">Tamura</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Takashi</namePart>
        <namePart type="family">Ninomiya</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper, we propose a new Transformer neural machine translation (NMT) model that incorporates dependency relations into self-attention on both source and target sides, dependency-based self-attention. The dependency-based self-attention is trained to attend to the modifiee for each token under constraints based on the dependency relations, inspired by Linguistically-Informed Self-Attention (LISA). While LISA is originally proposed for Transformer encoder for semantic role labeling, this paper extends LISA to Transformer NMT by masking future information on words in the decoder-side dependency-based self-attention. Additionally, our dependency-based self-attention operates at sub-word units created by byte pair encoding. The experiments show that our model improves 1.0 BLEU points over the baseline model on the WAT’18 Asian Scientific Paper Excerpt Corpus Japanese-to-English translation task.</abstract>
    <identifier type="citekey">deguchi-etal-2019-dependency</identifier>
    <identifier type="doi">10.26615/978-954-452-056-4_028</identifier>
    <location>
        <url>https://aclanthology.org/R19-1028</url>
    </location>
    <part>
        <date>2019-09</date>
        <extent unit="page">
            <start>239</start>
            <end>246</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Dependency-Based Self-Attention for Transformer NMT
%A Deguchi, Hiroyuki
%A Tamura, Akihiro
%A Ninomiya, Takashi
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F deguchi-etal-2019-dependency
%X In this paper, we propose a new Transformer neural machine translation (NMT) model that incorporates dependency relations into self-attention on both source and target sides, dependency-based self-attention. The dependency-based self-attention is trained to attend to the modifiee for each token under constraints based on the dependency relations, inspired by Linguistically-Informed Self-Attention (LISA). While LISA is originally proposed for Transformer encoder for semantic role labeling, this paper extends LISA to Transformer NMT by masking future information on words in the decoder-side dependency-based self-attention. Additionally, our dependency-based self-attention operates at sub-word units created by byte pair encoding. The experiments show that our model improves 1.0 BLEU points over the baseline model on the WAT’18 Asian Scientific Paper Excerpt Corpus Japanese-to-English translation task.
%R 10.26615/978-954-452-056-4_028
%U https://aclanthology.org/R19-1028
%U https://doi.org/10.26615/978-954-452-056-4_028
%P 239-246

Markdown (Informal)

[Dependency-Based Self-Attention for Transformer NMT](https://aclanthology.org/R19-1028) (Deguchi et al., RANLP 2019)

• Dependency-Based Self-Attention for Transformer NMT (Deguchi et al., RANLP 2019)

ACL

• Hiroyuki Deguchi, Akihiro Tamura, and Takashi Ninomiya. 2019. Dependency-Based Self-Attention for Transformer NMT. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 239–246, Varna, Bulgaria. INCOMA Ltd..