Papers › RelGAN: Relational Generative Adversarial Networks for Text Generation
RelGAN: Relational Generative Adversarial Networks for Text Generation
Weili Nie, Nina Narodytska, Ankit Patel
Generative adversarial networks (GANs) have achieved great success at generating realistic images. However, the text generation still remains a challenging task for modern GAN architectures. In this work, we propose RelGAN, a new GAN architecture for text generation, consisting of three main components: a relational memory based generator for the long-distance dependency modeling, the Gumbel-Softmax relaxation for training GANs on discrete data, and multiple embedded representations in the discriminator to provide a more informative signal for the generator updates. Our experiments show that RelGAN outperforms current state-of-the-art models in terms of sample quality and diversity, and we also reveal via ablation studies that each component of RelGAN contributes critically to its performance improvements. Moreover, a key advantage of our method, that distinguishes it from other GANs, is the ability to control the trade-off between sample quality and diversity via the use of a single adjustable parameter. Finally, RelGAN is the first architecture that makes GANs with Gumbel-Softmax relaxation succeed in generating realistic text.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Text Generation | COCO Captions | RelGAN (100) | BLEU-2 | 0.849 | #4 of 5 | Archive leaderboard | report |
| Text Generation | COCO Captions | RelGAN (100) | BLEU-3 | 0.687 | #4 of 5 | Archive leaderboard | report |
| Text Generation | COCO Captions | RelGAN (100) | BLEU-4 | 0.502 | #4 of 5 | Archive leaderboard | report |
| Text Generation | EMNLP2017 WMT | RelGAN | BLEU-2 | 0.881 | #3 of 5 | Archive leaderboard | report |
| Text Generation | EMNLP2017 WMT | RelGAN | BLEU-3 | 0.705 | #3 of 5 | Archive leaderboard | report |
| Text Generation | EMNLP2017 WMT | RelGAN | BLEU-4 | 0.501 | #3 of 5 | Archive leaderboard | report |
| Text Generation | EMNLP2017 WMT | RelGAN | BLEU-5 | 0.319 | #3 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections