Implicit Deep Latent Variable Models for Text Generation
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption is often made on the variational posteriors; and meanwhile (2) a notorious "posterior collapse" issue occurs. In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared with Gaussian-based posteriors. We further develop an LVM to directly match the aggregated posterior to the prior. It can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the "posterior collapse" issue. We demonstrate the effectiveness and versatility of our models in various text generation scenarios, including language modeling, unaligned style transfer, and dialog response generation. The source code to reproduce our experimental results is available on GitHub.
Code (1)
Tasks
Language ModelingLanguage ModellingResponse GenerationStyle TransferText GenerationSimilar Papers 제목 키워드 기반
Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck
Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong…
DecoderLanguage ModelingLanguage ModellingMachine Translation+6Contrastive Latent Variable Models for Neural Text Generation
Deep latent variable models such as variational autoencoders and energy-based models are widely used for neural text generation. Most of them focus on matching the prior distribution with the posterior distribution of th…
Contrastive LearningText GenerationBenefiting Deep Latent Variable Models via Learning the Prior and Removing Latent Regularization
There exist many forms of deep latent variable models, such as the variational autoencoder and adversarial autoencoder. Regardless of the specific class of model, there exists an implicit consensus that the latent distri…
DisentanglementDiversityImage GenerationImage-to-Image Translation+1Entropic Auto-Encoding via Implicit Free-Energy Minimization
Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition d…
Latent Dynamical Implicit Diffusion Processes
Latent dynamical models are commonly used to learn the distribution of a latent dynamical process that represents a sequence of noisy data samples. However, producing samples from such models with high fidelity is challe…