To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs - Sorbonne Université
Conference Papers Year : 2021

To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs

Thomas Scialom
  • Function : Author
  • PersonId : 1109225
Paul-Alexis Dray
  • Function : Author
  • PersonId : 1112181
Jacopo Staiano
  • Function : Author
  • PersonId : 1109226
Sylvain Lamprier

Abstract

Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. This is a much harder setting than for continuous tasks, which enjoy gradient flows from discriminators to generators, usually leading to dramatic learning instabilities. However, we claim that this can be solved by making discriminator and generator networks cooperate to produce output sequences during training. These cooperative outputs, inherently built to obtain higher discrimination scores, not only provide denser rewards for training, but also form a more compact artificial set for discriminator training, hence improving its accuracy and stability. In this paper, we show that our SelfGAN framework, built on this cooperative principle, outperforms Teacher Forcing and obtains state-of-the-art results on two challenging tasks, Summarization and Question Generation.
Fichier principal
Vignette du fichier
NeurIPS-2021-to-beam-or-not-to-beam-that-is-a-question-of-cooperation-for-language-gans-Paper.pdf (511.93 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03923314 , version 1 (04-01-2023)

Identifiers

  • HAL Id : hal-03923314 , version 1

Cite

Thomas Scialom, Paul-Alexis Dray, Jacopo Staiano, Sylvain Lamprier, Benjamin Piwowarski. To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs. Advances in Neural Information Processing Systems, Dec 2021, Virtual, United States. pp.26585--26597. ⟨hal-03923314⟩
35 View
16 Download

Share

More