Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis

Abstract

Generative Adversarial Networks (GAN) is a model for data synthesis, which creates plausible data through the competition of generator and discriminator. Although GAN application to image synthesis is extensively studied, it has inherent limitations to natural language generation. Because natural language is composed of discrete tokens, a generator has difficulty updating its gradient through backpropagation; therefore, most text-GAN studies generate sentences starting with a random token based on a reward system. Thus, the generators of previous studies are pre-trained in an autoregressive way before adversarial training, causing data memorization that synthesized sentences reproduce the training data. In this paper, we synthesize sentences using a framework similar to the original GAN. More specifically, we propose Text Embedding Space Generative Adversarial Networks (TESGAN) which generate continuous text embedding spaces instead of discrete tokens to solve the gradient backpropagation problem. Furthermore, TESGAN conducts unsupervised learning which does not directly refer to the text of the training data to overcome the data memorization issue. By adopting this novel method, TESGAN can synthesize new sentences, showing the potential of unsupervised learning for text synthesis. We expect to see extended research combining Large Language Models with a new perspective of viewing text as an continuous space.

NEJLT accpeted

References in corpus (12)

• Distilling the Knowledge in a Neural Network
• Training language models to follow instructions with human feedback
• LLaMA: Open and Efficient Foundation Language Models
• Flamingo: a Visual Language Model for Few-Shot Learning
• Scaling Instruction-Finetuned Language Models
• BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
• Alias-Free Generative Adversarial Networks
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks
• Adversarial Feature Matching for Text Generation
• Language Generation with Recurrent Generative Adversarial Networks without Pre-training