<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salton-kelleher-2019-persistence">
    <titleInfo>
        <title>Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Giancarlo</namePart>
        <namePart type="family">Salton</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Kelleher</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>Recurrent Neural Network Language Models composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results in Language Modeling. However, these models still struggle to process long sequences which are more likely to contain long-distance dependencies because of information fading. In this paper we demonstrate an effective mechanism for retrieving information in a memory augmented LSTM LM based on attending to information in memory in proportion to the number of timesteps the LSTM gating mechanism persisted the information.</abstract>
    <identifier type="citekey">salton-kelleher-2019-persistence</identifier>
    <identifier type="doi">10.26615/978-954-452-056-4_121</identifier>
    <location>
        <url>https://aclanthology.org/R19-1121</url>
    </location>
    <part>
        <date>2019-09</date>
        <extent unit="page">
            <start>1052</start>
            <end>1059</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists
%A Salton, Giancarlo
%A Kelleher, John
%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 salton-kelleher-2019-persistence
%X Recurrent Neural Network Language Models composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results in Language Modeling. However, these models still struggle to process long sequences which are more likely to contain long-distance dependencies because of information fading. In this paper we demonstrate an effective mechanism for retrieving information in a memory augmented LSTM LM based on attending to information in memory in proportion to the number of timesteps the LSTM gating mechanism persisted the information.
%R 10.26615/978-954-452-056-4_121
%U https://aclanthology.org/R19-1121
%U https://doi.org/10.26615/978-954-452-056-4_121
%P 1052-1059

Markdown (Informal)

[Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists](https://aclanthology.org/R19-1121) (Salton & Kelleher, RANLP 2019)

• Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists (Salton & Kelleher, RANLP 2019)

ACL

• Giancarlo Salton and John Kelleher. 2019. Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1052–1059, Varna, Bulgaria. INCOMA Ltd..