paper-with-me

홈 › Papers

Improve Variational Autoencoder for Text Generationwith Discrete Latent Bottleneck

2020-04-22 · Yang Zhao, Ping Yu, Suchismit Mahapatra, Qinliang Su, Changyou Chen

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 auto-regressive decoder. In this paper, we propose a principled approach to alleviate this issue by applying a discretized bottleneck to enforce an implicit latent feature matching in a more compact latent space. We impose a shared discrete latent space where each input is learned to choose a combination of latent atoms as a regularized latent representation. Our model endows a promising capability to model underlying semantics of discrete sequences and thus provide more interpretative latent structures. Empirically, we demonstrate our model's efficiency and effectiveness on a broad range of tasks, including language modeling, unaligned text style transfer, dialog response generation, and neural machine translation.

📄 PDF Abstract BibTeX arXiv:2004.10603

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderLanguage ModelingLanguage ModellingMachine TranslationRepresentation LearningResponse GenerationStyle TransferText GenerationText Style TransferTranslation

Similar Papers 제목 키워드 기반

An Introduction to Discrete Variational Autoencoders

2025-05-15 · Alan Jeffares, Liyuan Liu

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed la…

Decoder

Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders

2021-09-15 · Findings (EMNLP) 2021 11 · Giangiacomo Mercatali, André Freitas

The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous v…

DisentanglementStyle TransferText Style Transfer

Discrete Acoustic Space for an Efficient Sampling in Neural Text-To-Speech

2021-10-24 · Marek Strong, Jonas Rohnke, Antonio Bonafonte, Mateusz Łajszczak 외

We present a Split Vector Quantized Variational Autoencoder (SVQ-VAE) architecture using a split vector quantizer for NTTS, as an enhancement to the well-known Variational Autoencoder (VAE) and Vector Quantized Variation…

text-to-speechText to Speech

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders

2024-02-01 · Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann 외

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explaine…

Gaussian Mixture Vector Quantization with Aggregated Categorical Posterior

2024-10-14 · Mingyuan Yan, Jiawei Wu, Rushi Shah, Dianbo Liu

The vector quantization is a widely used method to map continuous representation to discrete space and has important application in tokenization for generative mode, bottlenecking information and many other tasks in mach…

Quantization