<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="felhi-etal-2021-challenging">
    <titleInfo>
        <title>Challenging the Semi-Supervised VAE Framework for Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ghazi</namePart>
        <namePart type="family">Felhi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Joseph</namePart>
        <namePart type="family">Le Roux</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Djamé</namePart>
        <namePart type="family">Seddah</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>Proceedings of the Second Workshop on Insights from Negative Results in NLP</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">João</namePart>
            <namePart type="family">Sedoc</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rogers</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Rumshisky</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Shabnam</namePart>
            <namePart type="family">Tafreshi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two sources of overcomplexity for which we provide simplifications. These simplifications to SSVAEs preserve their theoretical soundness while providing a number of practical advantages in the semi-supervised setup where the result of training is a text classifier. These simplifications are the removal of (i) the Kullback-Liebler divergence from its objective and (ii) the fully unobserved latent variable from its probabilistic model. These changes relieve users from choosing a prior for their latent variables, make the model smaller and faster, and allow for a better flow of information into the latent variables. We compare the simplified versions to standard SSVAEs on 4 text classification tasks. On top of the above-mentioned simplification, experiments show a speed-up of 26%, while keeping equivalent classification scores. The code to reproduce our experiments is public.</abstract>
    <identifier type="citekey">felhi-etal-2021-challenging</identifier>
    <identifier type="doi">10.18653/v1/2021.insights-1.19</identifier>
    <location>
        <url>https://aclanthology.org/2021.insights-1.19/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>136</start>
            <end>143</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Challenging the Semi-Supervised VAE Framework for Text Classification
%A Felhi, Ghazi
%A Le Roux, Joseph
%A Seddah, Djamé
%Y Sedoc, João
%Y Rogers, Anna
%Y Rumshisky, Anna
%Y Tafreshi, Shabnam
%S Proceedings of the Second Workshop on Insights from Negative Results in NLP
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F felhi-etal-2021-challenging
%X Semi-Supervised Variational Autoencoders (SSVAEs) are widely used models for data efficient learning. In this paper, we question the adequacy of the standard design of sequence SSVAEs for the task of text classification as we exhibit two sources of overcomplexity for which we provide simplifications. These simplifications to SSVAEs preserve their theoretical soundness while providing a number of practical advantages in the semi-supervised setup where the result of training is a text classifier. These simplifications are the removal of (i) the Kullback-Liebler divergence from its objective and (ii) the fully unobserved latent variable from its probabilistic model. These changes relieve users from choosing a prior for their latent variables, make the model smaller and faster, and allow for a better flow of information into the latent variables. We compare the simplified versions to standard SSVAEs on 4 text classification tasks. On top of the above-mentioned simplification, experiments show a speed-up of 26%, while keeping equivalent classification scores. The code to reproduce our experiments is public.
%R 10.18653/v1/2021.insights-1.19
%U https://aclanthology.org/2021.insights-1.19/
%U https://doi.org/10.18653/v1/2021.insights-1.19
%P 136-143

Markdown (Informal)

[Challenging the Semi-Supervised VAE Framework for Text Classification](https://aclanthology.org/2021.insights-1.19/) (Felhi et al., insights 2021)

• Challenging the Semi-Supervised VAE Framework for Text Classification (Felhi et al., insights 2021)

ACL

• Ghazi Felhi, Joseph Le Roux, and Djamé Seddah. 2021. Challenging the Semi-Supervised VAE Framework for Text Classification. In Proceedings of the Second Workshop on Insights from Negative Results in NLP, pages 136–143, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.