<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2020-self">
    <titleInfo>
        <title>Self-Attention with Cross-Lingual Position Representation</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">Dacheng</namePart>
        <namePart type="family">Tao</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>Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in cross-lingual scenarios, machine translation, the PEs of source and target sentences are modeled independently. Due to word order divergences in different languages, modeling the cross-lingual positional relationships might help SANs tackle this problem. In this paper, we augment SANs with cross-lingual position representations to model the bilingually aware latent structure for the input sentence. Specifically, we utilize bracketing transduction grammar (BTG)-based reordering information to encourage SANs to learn bilingual diagonal alignments. Experimental results on WMT’14 English$\Rightarrow$German, WAT’17 Japanese$\Rightarrow$English, and WMT’17 Chinese$\Leftrightarrow$English translation tasks demonstrate that our approach significantly and consistently improves translation quality over strong baselines. Extensive analyses confirm that the performance gains come from the cross-lingual information.</abstract>
    <identifier type="citekey">ding-etal-2020-self</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.153</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.153</url>
    </location>
    <part>
        <date>2020-jul</date>
        <extent unit="page">
            <start>1679</start>
            <end>1685</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Self-Attention with Cross-Lingual Position Representation
%A Ding, Liang
%A Wang, Longyue
%A Tao, Dacheng
%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 ding-etal-2020-self
%X Position encoding (PE), an essential part of self-attention networks (SANs), is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. However, in cross-lingual scenarios, machine translation, the PEs of source and target sentences are modeled independently. Due to word order divergences in different languages, modeling the cross-lingual positional relationships might help SANs tackle this problem. In this paper, we augment SANs with cross-lingual position representations to model the bilingually aware latent structure for the input sentence. Specifically, we utilize bracketing transduction grammar (BTG)-based reordering information to encourage SANs to learn bilingual diagonal alignments. Experimental results on WMT’14 English$\Rightarrow$German, WAT’17 Japanese$\Rightarrow$English, and WMT’17 Chinese$\Leftrightarrow$English translation tasks demonstrate that our approach significantly and consistently improves translation quality over strong baselines. Extensive analyses confirm that the performance gains come from the cross-lingual information.
%R 10.18653/v1/2020.acl-main.153
%U https://aclanthology.org/2020.acl-main.153
%U https://doi.org/10.18653/v1/2020.acl-main.153
%P 1679-1685

Markdown (Informal)

[Self-Attention with Cross-Lingual Position Representation](https://aclanthology.org/2020.acl-main.153) (Ding et al., ACL 2020)

• Self-Attention with Cross-Lingual Position Representation (Ding et al., ACL 2020)

ACL

• Liang Ding, Longyue Wang, and Dacheng Tao. 2020. Self-Attention with Cross-Lingual Position Representation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1679–1685, Online. Association for Computational Linguistics.