TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation

• URL: http://arxiv.org/abs/2011.13527v1
• Date: Fri, 27 Nov 2020 02:26:15 GMT
• Title: TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
• Authors: Chun-Hsing Lin, Siang-Ruei Wu, Hung-Yi Lee, Yun-Nung Chen
• Abstract summary: TaylorGAN is a novel approach to score function-based natural language generation. It augments the gradient estimation by off-policy update and the first-order Taylor expansion. It enables us to train NLG models from scratch with smaller batch size.
• Score: 79.4205462326301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.