A Hybrid Convolutional Variational Autoencoder for Text Generation

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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-02
Main Authors: Semeniuta, Stanislau, Severyn, Aliaksei, Erhardt Barth
Format: Article
Language:English
Subjects:
Architecture
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Semeniuta, Stanislau
Severyn, Aliaksei
Erhardt Barth
description 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 some of the major difficulties posed by training VAE models on textual data.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2074345322</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2074345322</sourcerecordid><originalsourceid>FETCH-proquest_journals_20743453223</originalsourceid><addsrcrecordid>eNqNjEEKgkAUQIcgSMo7DLQWpj-abU0qDyBtZcwvKDK__sxE3b4ID9DqvcXjLUQEWu-SQwqwErFzo1IK9jlkmY7EsZDVu-WhkyXZJ03BD2TNJK-GBzN7ETyhvVGHLHtiWePLywta5F-xEcveTA7jmWuxPZ_qskruTI-AzjcjBf6OXAMqT3WaaQD9X_UBwsI54g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2074345322</pqid></control><display><type>article</type><title>A Hybrid Convolutional Variational Autoencoder for Text Generation</title><source>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</source><creator>Semeniuta, Stanislau ; Severyn, Aliaksei ; Erhardt Barth</creator><creatorcontrib>Semeniuta, Stanislau ; Severyn, Aliaksei ; Erhardt Barth</creatorcontrib><description>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 some of the major difficulties posed by training VAE models on textual data.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Architecture</subject><ispartof>arXiv.org, 2017-02</ispartof><rights>2017. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2074345322?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25752,37011,44589</link.rule.ids></links><search><creatorcontrib>Semeniuta, Stanislau</creatorcontrib><creatorcontrib>Severyn, Aliaksei</creatorcontrib><creatorcontrib>Erhardt Barth</creatorcontrib><title>A Hybrid Convolutional Variational Autoencoder for Text Generation</title><title>arXiv.org</title><description>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 some of the major difficulties posed by training VAE models on textual data.</description><subject>Architecture</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjEEKgkAUQIcgSMo7DLQWpj-abU0qDyBtZcwvKDK__sxE3b4ID9DqvcXjLUQEWu-SQwqwErFzo1IK9jlkmY7EsZDVu-WhkyXZJ03BD2TNJK-GBzN7ETyhvVGHLHtiWePLywta5F-xEcveTA7jmWuxPZ_qskruTI-AzjcjBf6OXAMqT3WaaQD9X_UBwsI54g</recordid><startdate>20170208</startdate><enddate>20170208</enddate><creator>Semeniuta, Stanislau</creator><creator>Severyn, Aliaksei</creator><creator>Erhardt Barth</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20170208</creationdate><title>A Hybrid Convolutional Variational Autoencoder for Text Generation</title><author>Semeniuta, Stanislau ; Severyn, Aliaksei ; Erhardt Barth</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_20743453223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Architecture</topic><toplevel>online_resources</toplevel><creatorcontrib>Semeniuta, Stanislau</creatorcontrib><creatorcontrib>Severyn, Aliaksei</creatorcontrib><creatorcontrib>Erhardt Barth</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Semeniuta, Stanislau</au><au>Severyn, Aliaksei</au><au>Erhardt Barth</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Hybrid Convolutional Variational Autoencoder for Text Generation</atitle><jtitle>arXiv.org</jtitle><date>2017-02-08</date><risdate>2017</risdate><eissn>2331-8422</eissn><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 some of the major difficulties posed by training VAE models on textual data.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2017-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2074345322
source Publicly Available Content Database (Proquest) (PQ_SDU_P3)
subjects Architecture
title A Hybrid Convolutional Variational Autoencoder for Text Generation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T08%3A09%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20Hybrid%20Convolutional%20Variational%20Autoencoder%20for%20Text%20Generation&rft.jtitle=arXiv.org&rft.au=Semeniuta,%20Stanislau&rft.date=2017-02-08&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2074345322%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_20743453223%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2074345322&rft_id=info:pmid/&rfr_iscdi=true