@inproceedings{mercatali-freitas-2021-disentangling-generative,
title = "Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders",
author = "Mercatali, Giangiacomo and
Freitas, Andr{\'e}",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.301",
doi = "10.18653/v1/2021.findings-emnlp.301",
pages = "3547--3556",
abstract = "The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for images and text. We argue that despite being suitable for image datasets, continuous variables may not be ideal to model features of textual data, due to the fact that most generative factors in text are discrete. We propose a Variational Autoencoder based method which models language features as discrete variables and encourages independence between variables for learning disentangled representations. The proposed model outperforms continuous and discrete baselines on several qualitative and quantitative benchmarks for disentanglement as well as on a text style transfer downstream application.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mercatali-freitas-2021-disentangling-generative">
<titleInfo>
<title>Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giangiacomo</namePart>
<namePart type="family">Mercatali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Freitas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for images and text. We argue that despite being suitable for image datasets, continuous variables may not be ideal to model features of textual data, due to the fact that most generative factors in text are discrete. We propose a Variational Autoencoder based method which models language features as discrete variables and encourages independence between variables for learning disentangled representations. The proposed model outperforms continuous and discrete baselines on several qualitative and quantitative benchmarks for disentanglement as well as on a text style transfer downstream application.</abstract>
<identifier type="citekey">mercatali-freitas-2021-disentangling-generative</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.301</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.301</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3547</start>
<end>3556</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders
%A Mercatali, Giangiacomo
%A Freitas, André
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F mercatali-freitas-2021-disentangling-generative
%X The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for images and text. We argue that despite being suitable for image datasets, continuous variables may not be ideal to model features of textual data, due to the fact that most generative factors in text are discrete. We propose a Variational Autoencoder based method which models language features as discrete variables and encourages independence between variables for learning disentangled representations. The proposed model outperforms continuous and discrete baselines on several qualitative and quantitative benchmarks for disentanglement as well as on a text style transfer downstream application.
%R 10.18653/v1/2021.findings-emnlp.301
%U https://aclanthology.org/2021.findings-emnlp.301
%U https://doi.org/10.18653/v1/2021.findings-emnlp.301
%P 3547-3556
Markdown (Informal)
[Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders](https://aclanthology.org/2021.findings-emnlp.301) (Mercatali & Freitas, Findings 2021)
ACL