<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liza-grzes-2019-relating">
    <titleInfo>
        <title>Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Farhana</namePart>
        <namePart type="given">Ferdousi</namePart>
        <namePart type="family">Liza</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marek</namePart>
        <namePart type="family">Grzes</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Jason</namePart>
            <namePart type="family">Eisner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthias</namePart>
            <namePart type="family">Gallé</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jeffrey</namePart>
            <namePart type="family">Heinz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ariadna</namePart>
            <namePart type="family">Quattoni</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Guillaume</namePart>
            <namePart type="family">Rabusseau</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We analyse Recurrent Neural Networks (RNNs) to understand the significance of multiple LSTM layers. We argue that the Weighted Finite-state Automata (WFA) trained using a spectral learning algorithm are helpful to analyse RNNs. Our results suggest that multiple LSTM layers in RNNs help learning distributed hidden states, but have a smaller impact on the ability to learn long-term dependencies. The analysis is based on the empirical results, however relevant theory (whenever possible) was discussed to justify and support our conclusions.</abstract>
    <identifier type="citekey">liza-grzes-2019-relating</identifier>
    <identifier type="doi">10.18653/v1/W19-3903</identifier>
    <location>
        <url>https://aclanthology.org/W19-3903/</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>24</start>
            <end>33</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling
%A Liza, Farhana Ferdousi
%A Grzes, Marek
%Y Eisner, Jason
%Y Gallé, Matthias
%Y Heinz, Jeffrey
%Y Quattoni, Ariadna
%Y Rabusseau, Guillaume
%S Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence
%F liza-grzes-2019-relating
%X We analyse Recurrent Neural Networks (RNNs) to understand the significance of multiple LSTM layers. We argue that the Weighted Finite-state Automata (WFA) trained using a spectral learning algorithm are helpful to analyse RNNs. Our results suggest that multiple LSTM layers in RNNs help learning distributed hidden states, but have a smaller impact on the ability to learn long-term dependencies. The analysis is based on the empirical results, however relevant theory (whenever possible) was discussed to justify and support our conclusions.
%R 10.18653/v1/W19-3903
%U https://aclanthology.org/W19-3903/
%U https://doi.org/10.18653/v1/W19-3903
%P 24-33

Markdown (Informal)

[Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling](https://aclanthology.org/W19-3903/) (Liza & Grzes, ACL 2019)

• Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling (Liza & Grzes, ACL 2019)

ACL

• Farhana Ferdousi Liza and Marek Grzes. 2019. Relating RNN Layers with the Spectral WFA Ranks in Sequence Modelling. In Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges, pages 24–33, Florence. Association for Computational Linguistics.