LGCLMLApr 8, 2018

Language Modeling with Generative Adversarial Networks

arXiv:1804.02617v13 citations
Originality Synthesis-oriented
AI Analysis

This addresses the problem of unstable GAN training for language modeling, which is incremental as it builds on existing methods like WGANs.

The paper tackles the challenge of training Generative Adversarial Networks (GANs) for language generation, which is difficult due to discrete outputs causing instability, and finds that using a weaker regularization term in Wasserstein GANs improves training and convergence.

Generative Adversarial Networks (GANs) have been promising in the field of image generation, however, they have been hard to train for language generation. GANs were originally designed to output differentiable values, so discrete language generation is challenging for them which causes high levels of instability in training GANs. Consequently, past work has resorted to pre-training with maximum-likelihood or training GANs without pre-training with a WGAN objective with a gradient penalty. In this study, we present a comparison of those approaches. Furthermore, we present the results of some experiments that indicate better training and convergence of Wasserstein GANs (WGANs) when a weaker regularization term is enforcing the Lipschitz constraint.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes