<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="semeniuta-etal-2017-hybrid">
    <titleInfo>
        <title>A Hybrid Convolutional Variational Autoencoder for Text Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Stanislau</namePart>
        <namePart type="family">Semeniuta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aliaksei</namePart>
        <namePart type="family">Severyn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Erhardt</namePart>
        <namePart type="family">Barth</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Martha</namePart>
            <namePart type="family">Palmer</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rebecca</namePart>
            <namePart type="family">Hwa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Riedel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Copenhagen, Denmark</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper we explore the effect of architectural choices on learning a variational autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid the issue of the VAE collapsing to a deterministic model.</abstract>
    <identifier type="citekey">semeniuta-etal-2017-hybrid</identifier>
    <identifier type="doi">10.18653/v1/D17-1066</identifier>
    <location>
        <url>https://aclanthology.org/D17-1066</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>627</start>
            <end>637</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Hybrid Convolutional Variational Autoencoder for Text Generation
%A Semeniuta, Stanislau
%A Severyn, Aliaksei
%A Barth, Erhardt
%Y Palmer, Martha
%Y Hwa, Rebecca
%Y Riedel, Sebastian
%S Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F semeniuta-etal-2017-hybrid
%X In this paper we explore the effect of architectural choices on learning a variational autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we propose a novel hybrid architecture that blends fully feed-forward convolutional and deconvolutional components with a recurrent language model. Our architecture exhibits several attractive properties such as faster run time and convergence, ability to better handle long sequences and, more importantly, it helps to avoid the issue of the VAE collapsing to a deterministic model.
%R 10.18653/v1/D17-1066
%U https://aclanthology.org/D17-1066
%U https://doi.org/10.18653/v1/D17-1066
%P 627-637

Markdown (Informal)

[A Hybrid Convolutional Variational Autoencoder for Text Generation](https://aclanthology.org/D17-1066) (Semeniuta et al., EMNLP 2017)

• A Hybrid Convolutional Variational Autoencoder for Text Generation (Semeniuta et al., EMNLP 2017)

ACL

• Stanislau Semeniuta, Aliaksei Severyn, and Erhardt Barth. 2017. A Hybrid Convolutional Variational Autoencoder for Text Generation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 627–637, Copenhagen, Denmark. Association for Computational Linguistics.