<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosendahl-etal-2019-analysis">
    <titleInfo>
        <title>Analysis of Positional Encodings for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jan</namePart>
        <namePart type="family">Rosendahl</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Viet</namePart>
        <namePart type="given">Anh</namePart>
        <namePart type="given">Khoa</namePart>
        <namePart type="family">Tran</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiyue</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hermann</namePart>
        <namePart type="family">Ney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-nov&quot; 2-3&quot;</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th International Conference on Spoken Language Translation</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Hong Kong</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this work we analyze and compare the behavior of the Transformer architecture when using different positional encoding methods. While absolute and relative positional encoding perform equally strong overall, we show that relative positional encoding is vastly superior (4.4% to 11.9% BLEU) when translating a sentence that is longer than any observed training sentence. We further propose and analyze variations of relative positional encoding and observe that the number of trainable parameters can be reduced without a performance loss, by using fixed encoding vectors or by removing some of the positional encoding vectors.</abstract>
    <identifier type="citekey">rosendahl-etal-2019-analysis</identifier>
    <location>
        <url>https://aclanthology.org/2019.iwslt-1.20</url>
    </location>
    <part>
        <date>2019-nov&quot; 2-3&quot;</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Analysis of Positional Encodings for Neural Machine Translation
%A Rosendahl, Jan
%A Tran, Viet Anh Khoa
%A Wang, Weiyue
%A Ney, Hermann
%S Proceedings of the 16th International Conference on Spoken Language Translation
%D 2019
%8 nov" 2 3"
%I Association for Computational Linguistics
%C Hong Kong
%F rosendahl-etal-2019-analysis
%X In this work we analyze and compare the behavior of the Transformer architecture when using different positional encoding methods. While absolute and relative positional encoding perform equally strong overall, we show that relative positional encoding is vastly superior (4.4% to 11.9% BLEU) when translating a sentence that is longer than any observed training sentence. We further propose and analyze variations of relative positional encoding and observe that the number of trainable parameters can be reduced without a performance loss, by using fixed encoding vectors or by removing some of the positional encoding vectors.
%U https://aclanthology.org/2019.iwslt-1.20

Markdown (Informal)

[Analysis of Positional Encodings for Neural Machine Translation](https://aclanthology.org/2019.iwslt-1.20) (Rosendahl et al., IWSLT 2019)

• Analysis of Positional Encodings for Neural Machine Translation (Rosendahl et al., IWSLT 2019)

ACL

• Jan Rosendahl, Viet Anh Khoa Tran, Weiyue Wang, and Hermann Ney. 2019. Analysis of Positional Encodings for Neural Machine Translation. In Proceedings of the 16th International Conference on Spoken Language Translation, Hong Kong. Association for Computational Linguistics.