Abstract: Aiming at the problems of accumulated errors caused by the supervised form of the current generative adversarial network text generation model  and the single generated text information, a text generation model based on GRU  generative adversarial network is proposed. The GRU generator uses rollout-policy to update parameters, and Monte Carlo search is added into the model to generate sample sequences. The GRU neural network with fewer parameters is used as the generator and the discriminator. The output loss function of the discriminator guides the parameter optimization in the generation process, and the Monte Carlo strategy is used to supplement the incomplete sequence in the generation process to reduce the accumulation of errors and increase the text richness of generated information. This paper introduces the gate truncation mechanism, replaces the sigmoid function in the GRU network with a custom function, improves the activation function of the implicit variable at the current time, and improves the slower convergence speed of the original function and the problem of gradient disappearance, making it more suitable for this model. The results of simulation experiments show that this model enriches the diversity of text generation, improves the convergence speed of the model, and proves the effectiveness of this model. The model has good applicability.

Key words: GAN, text generation, GRU(Gated Recurrent Unit) neural network, Monte Carlo strategy