Adversarial Ranking for Language Generation

NeurIPS 2017 Kevin LinDianqi LiXiaodong HeZhengyou ZhangMing-Ting Sun

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... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

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 # 3
BLEU-3 0.478 # 3
BLEU-4 0.411 # 3
BLEU-5 0.463 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet