Generative Cooperative Networks for Natural Language Generation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Generative Cooperative Networks for Natural Language Generation

Abstract

Generative Adversarial Networks (GANs) have known a tremendous success for many continuous generation tasks, especially in the field of image generation. However, for discrete outputs such as language, optimizing GANs remains an open problem with many instabilities, as no gradient can be properly back-propagated from the discriminator output to the generator parameters. An alternative is to learn the generator network via reinforcement learning, using the discriminator signal as a reward, but such a technique suffers from moving rewards and vanishing gradient problems. Finally, it often falls short compared to direct maximum-likelihood approaches. In this paper, we introduce Generative Cooperative Networks, in which the discriminator architecture is cooperatively used along with the generation policy to output samples of realistic texts for the task at hand. We give theoretical guarantees of convergence for our approach, and study various efficient decoding schemes to empirically achieve state-of-the-art results in two main NLG tasks.
Fichier principal
Vignette du fichier
lamprier22a.pdf (623.01 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03736116 , version 1 (22-07-2022)

Identifiers

  • HAL Id : hal-03736116 , version 1

Cite

Sylvain Lamprier, Thomas Scialom, Antoine Chaffin, Vincent Claveau, Ewa Kijak, et al.. Generative Cooperative Networks for Natural Language Generation. ICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, MD, United States. pp.11891--11905. ⟨hal-03736116⟩
69 View
53 Download

Share

Gmail Facebook Twitter LinkedIn More