02/02/2021

TextGAIL: Generative Adversarial Imitation Learning for Text Generation

Qingyang Wu, Lei Li, Zhou Yu

Keywords:

Abstract Paper Similar Papers

Abstract: Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts. We suspect previous text GANs' inferior performance is due to the lack of a reliable guiding signal in their discriminators. To address this problem, we propose a generative adversarial imitation learning framework for text generation that uses large pre-trained language models to provide more reliable reward guidance. As previous text GANs suffer from high variance of gradients, we apply contrastive discriminator, and proximal policy optimization (PPO) to stabilize and improve text generation performance. For evaluation, we conduct experiments on a diverse set of unconditional and conditional text generation tasks. Experimental results show that TextGAIL achieves better performance in terms of both quality and diversity than the MLE baseline. We also validate our intuition that TextGAIL's discriminator demonstrates the capability of providing reasonable rewards with an additional task.

The video of this talk cannot be embedded. You can watch it here:
https://slideslive.com/38948462
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at AAAI 2021 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 3:19 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 1
 4:49 
 0
 0
 0
 0
 5:44 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 11:39 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 11:18 
 0
 0
 0
 0
 6:03 
 0
 0
 0
 0
 5:10 
 0
 0
 0
 0
 5:16 
 0
 0
 0
 0
 4:38 
 0
 0
 0
 0
 9:16 
 0
 0
 0
 0
 5:32 
 0
 0
 0
 0
 11:44 
 0
 0
 0
 0
 9:11 
 0
 0
 0
 0
 4:46 
 0
 0
 0
 0
 10:58 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 5:06 
 0
 0
 0
 0
 11:26 
 0
 0
 0
 0
 3:18 
 0
 0
 0
 0
 14:26 
 0
 0
 0
 0
 5:55 
 0
 0
 0
 0
 13:34 
 0
 0
 0
 0
 11:36 
 0
 0
 0
 0
 6:27 
 0
 0
 0
 0
 14:00 
 0
 0
 0
 0
 12:19 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 15:04 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 13:17 
 0
 0
 0
 0
 17:39 
 0
 0
 0
 0
 12:18 
 0
 0
 0
 1
 12:13 
 0
 0
 0
 0
 4:20 
 0
 0
 0
 0
 3:21 
 0
 0
 0
 0
 12:46 
 0
 0
 0
 0
 4:25