<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-improving-variational">
    <titleInfo>
        <title>Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ruizhe</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiao</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guanyi</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenghua</namePart>
        <namePart type="family">Lin</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>The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.</abstract>
    <identifier type="citekey">li-etal-2020-improving-variational</identifier>
    <identifier type="doi">10.18653/v1/2020.coling-main.216</identifier>
    <location>
        <url>https://aclanthology.org/2020.coling-main.216</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>2381</start>
            <end>2397</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation
%A Li, Ruizhe
%A Li, Xiao
%A Chen, Guanyi
%A Lin, Chenghua
%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 li-etal-2020-improving-variational
%X The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling, where the approximate posterior collapses to the prior, and the model will totally ignore the latent variables and be degraded to a plain language model during text generation. Such an issue is particularly prevalent when RNN-based VAE models are employed for text modelling. In this paper, we propose a simple, generic architecture called Timestep-Wise Regularisation VAE (TWR-VAE), which can effectively avoid posterior collapse and can be applied to any RNN-based VAE models. The effectiveness and versatility of our model are demonstrated in different tasks, including language modelling and dialogue response generation.
%R 10.18653/v1/2020.coling-main.216
%U https://aclanthology.org/2020.coling-main.216
%U https://doi.org/10.18653/v1/2020.coling-main.216
%P 2381-2397

Markdown (Informal)

[Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation](https://aclanthology.org/2020.coling-main.216) (Li et al., COLING 2020)

• Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation (Li et al., COLING 2020)

ACL

• Ruizhe Li, Xiao Li, Guanyi Chen, and Chenghua Lin. 2020. Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2381–2397, Barcelona, Spain (Online). International Committee on Computational Linguistics.