@inproceedings{serban-etal-2017-piecewise-latent,
title = "Piecewise Latent Variables for Neural Variational Text Processing",
author = "Serban, Iulian Vlad and
Ororbia II, Alexander and
Pineau, Joelle and
Courville, Aaron",
editor = "Chang, Kai-Wei and
Chang, Ming-Wei and
Srikumar, Vivek and
Rush, Alexander M.",
booktitle = "Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-4308",
doi = "10.18653/v1/W17-4308",
pages = "52--62",
abstract = "Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="serban-etal-2017-piecewise-latent">
<titleInfo>
<title>Piecewise Latent Variables for Neural Variational Text Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iulian</namePart>
<namePart type="given">Vlad</namePart>
<namePart type="family">Serban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Ororbia II</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joelle</namePart>
<namePart type="family">Pineau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Courville</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 2nd Workshop on Structured Prediction for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Rush</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>Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.</abstract>
<identifier type="citekey">serban-etal-2017-piecewise-latent</identifier>
<identifier type="doi">10.18653/v1/W17-4308</identifier>
<location>
<url>https://aclanthology.org/W17-4308</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>52</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Piecewise Latent Variables for Neural Variational Text Processing
%A Serban, Iulian Vlad
%A Ororbia II, Alexander
%A Pineau, Joelle
%A Courville, Aaron
%Y Chang, Kai-Wei
%Y Chang, Ming-Wei
%Y Srikumar, Vivek
%Y Rush, Alexander M.
%S Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F serban-etal-2017-piecewise-latent
%X Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich, multi-modal latent factors in real-world data, such as natural language text. However, current models often assume simplistic priors on the latent variables - such as the uni-modal Gaussian distribution - which are incapable of representing complex latent factors efficiently. To overcome this restriction, we propose the simple, but highly flexible, piecewise constant distribution. This distribution has the capacity to represent an exponential number of modes of a latent target distribution, while remaining mathematically tractable. Our results demonstrate that incorporating this new latent distribution into different models yields substantial improvements in natural language processing tasks such as document modeling and natural language generation for dialogue.
%R 10.18653/v1/W17-4308
%U https://aclanthology.org/W17-4308
%U https://doi.org/10.18653/v1/W17-4308
%P 52-62
Markdown (Informal)
[Piecewise Latent Variables for Neural Variational Text Processing](https://aclanthology.org/W17-4308) (Serban et al., 2017)
ACL