May 31, 2017 · In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than ...

In this paper, we propose a novel adversarial learning framework, RankGAN, for generating high- quality language descriptions. RankGAN learns the model from the ...

In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions.

This paper proposes a novel generative adversarial network, RankGAN, for generating high-quality language descriptions by viewing a set of data samples ...

Apply Generative Adversarial Nets to generating sequences of discrete tokens with optimization via replacing the discriminator with a ranker.

Sep 6, 2024 · In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than ...

The paper proposes an alternative parameterization of the GAN discriminator based on relative ranks among a comparison set. The method shows better quantitative ...

While the goal of previous works is to retrieve relevant documents, our proposed model takes the ranking scores as the rewards to learn the language generator.

Adversarial-Ranking-for-Language-Generation ... This paper is conceptually an extention of SeqGAN (https://arxiv.org/abs/1609.05473). And SeqGAN code from https ...

Text Generation on COCO Captions ; 1. LeakGAN. 0.950 ; 2. partGAN. 0.910 ; 3. RankGAN. 0.850 ; 4. RelGAN (100). 0.849 ...