@inproceedings{balasubramanian-etal-2021-polarized,
title = "Polarized-{VAE}: Proximity Based Disentangled Representation Learning for Text Generation",
author = "Balasubramanian, Vikash and
Kobyzev, Ivan and
Bahuleyan, Hareesh and
Shapiro, Ilya and
Vechtomova, Olga",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.32",
doi = "10.18653/v1/2021.eacl-main.32",
pages = "416--423",
abstract = "Learning disentangled representations of realworld data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the factorization in the latent space of models such as the variational autoencoder (VAE) by training with task-specific losses. In this work, we propose polarized-VAE, an approach that disentangles select attributes in the latent space based on proximity measures reflecting the similarity between data points with respect to these attributes. We apply our method to disentangle the semantics and syntax of sentences and carry out transfer experiments. Polarized-VAE outperforms the VAE baseline and is competitive with state-of-the-art approaches, while being more a general framework that is applicable to other attribute disentanglement tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balasubramanian-etal-2021-polarized">
<titleInfo>
<title>Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vikash</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Kobyzev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hareesh</namePart>
<namePart type="family">Bahuleyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilya</namePart>
<namePart type="family">Shapiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Vechtomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning disentangled representations of realworld data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the factorization in the latent space of models such as the variational autoencoder (VAE) by training with task-specific losses. In this work, we propose polarized-VAE, an approach that disentangles select attributes in the latent space based on proximity measures reflecting the similarity between data points with respect to these attributes. We apply our method to disentangle the semantics and syntax of sentences and carry out transfer experiments. Polarized-VAE outperforms the VAE baseline and is competitive with state-of-the-art approaches, while being more a general framework that is applicable to other attribute disentanglement tasks.</abstract>
<identifier type="citekey">balasubramanian-etal-2021-polarized</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.32</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.32</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>416</start>
<end>423</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation
%A Balasubramanian, Vikash
%A Kobyzev, Ivan
%A Bahuleyan, Hareesh
%A Shapiro, Ilya
%A Vechtomova, Olga
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F balasubramanian-etal-2021-polarized
%X Learning disentangled representations of realworld data is a challenging open problem. Most previous methods have focused on either supervised approaches which use attribute labels or unsupervised approaches that manipulate the factorization in the latent space of models such as the variational autoencoder (VAE) by training with task-specific losses. In this work, we propose polarized-VAE, an approach that disentangles select attributes in the latent space based on proximity measures reflecting the similarity between data points with respect to these attributes. We apply our method to disentangle the semantics and syntax of sentences and carry out transfer experiments. Polarized-VAE outperforms the VAE baseline and is competitive with state-of-the-art approaches, while being more a general framework that is applicable to other attribute disentanglement tasks.
%R 10.18653/v1/2021.eacl-main.32
%U https://aclanthology.org/2021.eacl-main.32
%U https://doi.org/10.18653/v1/2021.eacl-main.32
%P 416-423
Markdown (Informal)
[Polarized-VAE: Proximity Based Disentangled Representation Learning for Text Generation](https://aclanthology.org/2021.eacl-main.32) (Balasubramanian et al., EACL 2021)
ACL