DP-GAN: Diversity-Promoting Generative Adversarial Network for Generating Informative and Diversified Text
This addresses the issue of boring text generation for NLP applications, though it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of repetitive and uninformative text generation by proposing DP-GAN, which uses a novel reward system and language-model discriminator to encourage diversity, resulting in substantially more diverse and informative text in review and dialogue generation tasks.
Existing text generation methods tend to produce repeated and "boring" expressions. To tackle this problem, we propose a new text generation model, called Diversity-Promoting Generative Adversarial Network (DP-GAN). The proposed model assigns low reward for repeatedly generated text and high reward for "novel" and fluent text, encouraging the generator to produce diverse and informative text. Moreover, we propose a novel language-model based discriminator, which can better distinguish novel text from repeated text without the saturation problem compared with existing classifier-based discriminators. The experimental results on review generation and dialogue generation tasks demonstrate that our model can generate substantially more diverse and informative text than existing baselines. The code is available at https://github.com/lancopku/DPGAN