Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation (2004.02135v5)

Abstract: The autoregressive LLM (ALM) trained with maximum likelihood estimation (MLE) is widely used in unconditional text generation. Due to exposure bias, the generated texts still suffer from low quality and diversity. This presents statistically as a discrepancy between the real text and generated text. Some research shows a discriminator can detect this discrepancy. Because the discriminator can encode more information than the generator, discriminator has the potentiality to improve generator. To alleviate the exposure bias, generative adversarial networks (GAN) use the discriminator to update the generator's parameters directly, but they fail by being evaluated precisely. A critical reason for the failure is the difference between the discriminator input and the ALM input. We propose a novel mechanism by adding a filter which has the same input as the discriminator. First, discriminator detects the discrepancy signals and passes to filter directly (or by learning). Then, we use the filter to reject some generated samples with a sampling-based method. Thus, the original generative distribution is revised to reduce the discrepancy. Two ALMs, RNN-based and Transformer-based, are experimented. Evaluated precisely by three metrics, our mechanism consistently outperforms the ALMs and all kinds of GANs across two benchmark data sets.