SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

18 Sep 2016 Lantao Yu Wei-Nan Zhang Jun Wang Yong Yu

As a new way of training generative models, Generative Adversarial Nets (GAN) that uses a discriminative model to guide the training of the generative model has enjoyed considerable success in generating real-valued data. However, it has limitations when the goal is for generating sequences of discrete tokens... (read more)

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Text Generation Chinese Poems SeqGAN BLEU-2 0.738 # 2
Text Generation COCO Captions SeqGAN BLEU-2 0.831 # 5
BLEU-3 0.642 # 5
BLEU-4 0.521 # 3
BLEU-5 0.427 # 4
Text Generation EMNLP2017 WMT SeqGAN BLEU-2 0.859 # 3
BLEU-3 0.6015 # 3
BLEU-4 0.4541 # 3
BLEU-5 0.4498 # 3

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions
GAN
Generative Models