Stylized Text Generation Using Wasserstein Autoencoders with a Mixture of Gaussian Prior
Wasserstein autoencoders are effective for text generation. They do not however provide any control over the style and topic of the generated sentences if the dataset has multiple classes and includes different topics. In this work, we present a semi-supervised approach for generating stylized sentences. Our model is trained on a multi-class dataset and learns the latent representation of the sentences using a mixture of Gaussian prior without any adversarial losses. This allows us to generate sentences in the style of a specified class or multiple classes by sampling from their corresponding prior distributions. Moreover, we can train our model on relatively small datasets and learn the latent representation of a specified class by adding external data with other styles/classes to our dataset. While a simple WAE or VAE cannot generate diverse sentences in this case, generated sentences with our approach are diverse, fluent, and preserve the style and the content of the desired classes.
Code (0)
등록된 구현이 없습니다.
Tasks
Text GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
Relational regularized autoencoder (RAE) is a framework to learn the distribution of data by minimizing a reconstruction loss together with a relational regularization on the latent space. A recent attempt to reduce the …
Image GenerationDialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder
Variational autoencoders~(VAEs) have shown a promise in data-driven conversation modeling. However, most VAE conversation models match the approximate posterior distribution over the latent variables to a simple prior su…
Response GenerationGaussian mixture models with Wasserstein distance
Generative models with both discrete and continuous latent variables are highly motivated by the structure of many real-world data sets. They present, however, subtleties in training often manifesting in the discrete lat…
DescriptiveTraining-free Stylized Text-to-Image Generation with Fast Inference
Although diffusion models exhibit impressive generative capabilities, existing methods for stylized image generation based on these models often require textual inversion or fine-tuning with style images, which is time-c…
Image GenerationText to Image GenerationText-to-Image GenerationSymmetric Wasserstein Autoencoders
Leveraging the framework of Optimal Transport, we introduce a new family of generative autoencoders with a learnable prior, called Symmetric Wasserstein Autoencoders (SWAEs). We propose to symmetrically match the joint d…
DecoderDenoising