@inproceedings{boenninghoff-etal-2020-variational,
title = "Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution",
author = "Boenninghoff, Benedikt and
Zeiler, Steffen and
Nickel, Robert and
Kolossa, Dorothea",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.45",
doi = "10.18653/v1/2020.coling-main.45",
pages = "519--529",
abstract = "Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. Variational autoencoders (VAEs) have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending a VAE with an embedded Gaussian mixture model to a Student-t mixture model, which allows for an independent control of the {``}heaviness{''} of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="boenninghoff-etal-2020-variational">
<titleInfo>
<title>Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Benedikt</namePart>
<namePart type="family">Boenninghoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steffen</namePart>
<namePart type="family">Zeiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Nickel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorothea</namePart>
<namePart type="family">Kolossa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. Variational autoencoders (VAEs) have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending a VAE with an embedded Gaussian mixture model to a Student-t mixture model, which allows for an independent control of the “heaviness” of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method.</abstract>
<identifier type="citekey">boenninghoff-etal-2020-variational</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.45</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.45</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>519</start>
<end>529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution
%A Boenninghoff, Benedikt
%A Zeiler, Steffen
%A Nickel, Robert
%A Kolossa, Dorothea
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F boenninghoff-etal-2020-variational
%X Traditional computational authorship attribution describes a classification task in a closed-set scenario. Given a finite set of candidate authors and corresponding labeled texts, the objective is to determine which of the authors has written another set of anonymous or disputed texts. In this work, we propose a probabilistic autoencoding framework to deal with this supervised classification task. Variational autoencoders (VAEs) have had tremendous success in learning latent representations. However, existing VAEs are currently still bound by limitations imposed by the assumed Gaussianity of the underlying probability distributions in the latent space. In this work, we are extending a VAE with an embedded Gaussian mixture model to a Student-t mixture model, which allows for an independent control of the “heaviness” of the respective tails of the implied probability densities. Experiments over an Amazon review dataset indicate superior performance of the proposed method.
%R 10.18653/v1/2020.coling-main.45
%U https://aclanthology.org/2020.coling-main.45
%U https://doi.org/10.18653/v1/2020.coling-main.45
%P 519-529
Markdown (Informal)
[Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution](https://aclanthology.org/2020.coling-main.45) (Boenninghoff et al., COLING 2020)
ACL