Abstract
Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode collapse. To tackle these problems, we propose a novel mechanism. It first segments the entire sequence into several sub-sequences. Then these sub-sequences, together with the entire sequence, are evaluated individually by the discriminator. At last these feedback signals are all used to guide the learning of GAN. This mechanism learns the generation of both the entire sequence and the sub-sequences simultaneously. Learning to generate sub-sequences is easy and is helpful in generating an entire sequence. It is easy to improve the existing GAN-based models with this mechanism. We rebuild three previous well-designed models with our mechanism, and the experimental results on benchmark data show these models are improved significantly, the best one outperforms the state-of-the-art model.\footnote[1]{All code and data are available at https://github.com/liyzcj/seggan.git
Abstract (translated)
为了减少文本的曝光偏差,成功地引入了生成对抗网(gan)。然而,这些模型中的鉴频器只评估整个序列,从而导致反馈稀疏和模式崩溃。为了解决这些问题,我们提出了一种新的机制。它首先将整个序列分割成几个子序列。然后,这些子序列连同整个序列一起被鉴别器单独地评估。最后,这些反馈信号都被用来指导氮化镓的学习。该机制同时学习整个序列和子序列的生成。学习生成子序列很容易,并且有助于生成整个序列。利用这种机制可以很容易地改进现有的基于氮化镓的模型。我们用我们的机制重新构建了之前三个设计良好的模型,基准数据的实验结果表明这些模型得到了显著的改进,最好的模型优于最先进的模型。footnote[1]所有代码和数据都可以在https://github.com/liyzcj/seggan.git上找到。
URL
https://arxiv.org/abs/1905.12835