Adversarial Ranking for Language Generation

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions... In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than training the discriminator to learn and assign absolute binary predicate for individual data sample, the proposed RankGAN is able to analyze and rank a collection of human-written and machine-written sentences by giving a reference group. By viewing a set of data samples collectively and evaluating their quality through relative ranking scores, the discriminator is able to make better assessment which in turn helps to learn a better generator. The proposed RankGAN is optimized through the policy gradient technique. Experimental results on multiple public datasets clearly demonstrate the effectiveness of the proposed approach. read more

PDF Abstract NeurIPS 2017 PDF NeurIPS 2017 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text Generation Chinese Poems RankGAN BLEU-2 0.812 # 1
Text Generation COCO Captions RankGAN BLEU-2 0.850 # 3
BLEU-3 0.672 # 4
BLEU-4 0.557 # 2
BLEU-5 0.544 # 3
Text Generation EMNLP2017 WMT RankGAN BLEU-2 0.778 # 4
BLEU-3 0.478 # 4
BLEU-4 0.411 # 4
BLEU-5 0.463 # 2

Methods


No methods listed for this paper. Add relevant methods here