Variational Autoencoders
Related Papers
Piecewise Latent Variables for Neural Variational Text Processing
AbstractAdvances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn …...
A Hierarchical Latent Structure for Variational Conversation Modeling
AbstractVariational autoencoders (VAE) combined with hierarchical RNNs have emerged as a powerful framework for conversation modeling. However, they suffer from the notorious degeneration problem, where the decoders learn to ignore …...
Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing
AbstractVariational autoencoders (VAE) with an auto-regressive decoder have been applied for many natural language processing (NLP) tasks. VAE objective consists of two terms, the KL regularization term and the reconstruction …...
Generating Sentences from Disentangled Syntactic and Semantic Spaces
AbstractVariational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space. However, generating sentences from the continuous latent space does not explicitly model …...
Generative latent neural models for automatic word alignment
Word alignments identify translational correspondences between words in a parallel sentence pair and are used, for instance, to learn bilingual dictionaries, to train statistical machine trans- lation systems or to …...
On the Encoder-Decoder Incompatibility in Variational Text Modeling and Beyond
AbstractVariational autoencoders (VAEs) combine latent variables with amortized variational inference, whose optimization usually converges into a trivial local optimum termed posterior collapse, especially in text modeling. By tracking the optimization …...
Variational Autoencoder with Embedded Student-t Mixture Model for Authorship Attribution
AbstractTraditional 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 …...
Disentangling Representations of Text by Masking Transformers
AbstractRepresentations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a range of downstream tasks. In this paper we …...
FlowPrior: Learning Expressive Priors for Latent Variable Sentence Models
AbstractVariational autoencoders (VAEs) are widely used for latent variable modeling of text. We focus on variations that learn expressive prior distributions over the latent variable. We find that existing training …...
Generative Text Modeling through Short Run Inference
AbstractLatent variable models for text, when trained successfully, accurately model the data distribution and capture global semantic and syntactic features of sentences. The prominent approach to train such models is …...
Learning Robust Latent Representations for Controllable Speech Synthesis
State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable text-to-speech (TTS) …...
Perceptual Models of Machine-Edited Text
We introduce a novel dataset of human judg- ments of machine-edited text and initial mod- els of those perceptions. Six machine-editing methods ranging from character swapping to variational autoencoders are …...
Controlled Text Generation Using Dictionary Prior in Variational Autoencoders
AbstractWhile variational autoencoders (VAEs) have been widely applied in text generation tasks, they are troubled by two challenges: insufficient representation capacity and poor controllability. The former results from the posterior …...