Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder

by   Yuchi Zhang, et al.

Diversity plays a vital role in many text generating applications. In recent years, Conditional Variational Auto Encoders (CVAE) have shown promising performances for this task. However, they often encounter the so called KL-Vanishing problem. Previous works mitigated such problem by heuristic methods such as strengthening the encoder or weakening the decoder while optimizing the CVAE objective function. Nevertheless, the optimizing direction of these methods are implicit and it is hard to find an appropriate degree to which these methods should be applied. In this paper, we propose an explicit optimizing objective to complement the CVAE to directly pull away from KL-vanishing. In fact, this objective term guides the encoder towards the "best encoder" of the decoder to enhance the expressiveness. A labeling network is introduced to estimate the "best encoder". It provides a continuous label in the latent space of CVAE to help build a close connection between latent variables and targets. The whole proposed method is named Self Labeling CVAE (SLCVAE). To accelerate the research of diverse text generation, we also propose a large native one-to-many dataset. Extensive experiments are conducted on two tasks, which show that our method largely improves the generating diversity while achieving comparable accuracy compared with state-of-art algorithms.


page 1

page 2

page 3

page 4


Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generation

The past several years have witnessed Variational Auto-Encoder's superio...

PCAE: A Framework of Plug-in Conditional Auto-Encoder for Controllable Text Generation

Controllable text generation has taken a gigantic step forward these day...

Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation

Variational Auto-Encoder (VAE) has been widely adopted in text generatio...

Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders

Current neural Natural Language Generation (NLG) models cannot handle em...

Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors

Generating high quality texts with high diversity is important for many ...

Byte-Level Recursive Convolutional Auto-Encoder for Text

This article proposes to auto-encode text at byte-level using convolutio...

Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing

Variational autoencoders (VAEs) with an auto-regressive decoder have bee...

Please sign up or login with your details

Forgot password? Click here to reset