论文标题
泰勒根（Taylorgan）：样本效率自然语言生成的邻居授权政策更新
TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
论文作者
论文摘要
通常，基于得分功能的自然语言产生（NLG）方法（例如增强）通常会遭受样本效率低下和训练不稳定性问题的困扰。这主要是由于离散空间采样的非差异性质，因此这些方法必须将鉴别器视为黑匣子并忽略梯度信息。为了提高样品效率并降低了增强的方差，我们提出了一种新型方法Taylorgan，该方法通过非政策更新和一阶Taylor扩展来增强梯度估计。这种方法使我们能够以较小的批次尺寸从头开始训练NLG模型 - 没有最大似然前训练，并且在质量和多样性的多种指标上都超过了现有的基于GAN的方法。源代码和数据可从https://github.com/miulab/taylorgan获得
Score function-based natural language generation (NLG) approaches such as REINFORCE, in general, suffer from low sample efficiency and training instability problems. This is mainly due to the non-differentiable nature of the discrete space sampling and thus these methods have to treat the discriminator as a black box and ignore the gradient information. To improve the sample efficiency and reduce the variance of REINFORCE, we propose a novel approach, TaylorGAN, which augments the gradient estimation by off-policy update and the first-order Taylor expansion. This approach enables us to train NLG models from scratch with smaller batch size -- without maximum likelihood pre-training, and outperforms existing GAN-based methods on multiple metrics of quality and diversity. The source code and data are available at https://github.com/MiuLab/TaylorGAN
