Long Text Generation via Adversarial Training with Leaked Information

24 Sep 2017  ·  Jiaxian Guo, Sidi Lu, Han Cai, Wei-Nan Zhang, Yong Yu, Jun Wang ·

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that use a discriminative model to guide the training of the generative model as a reinforcement learning policy has shown promising results in text generation... However, the scalar guiding signal is only available after the entire text has been generated and lacks intermediate information about text structure during the generative process. As such, it limits its success when the length of the generated text samples is long (more than 20 words). In this paper, we propose a new framework, called LeakGAN, to address the problem for long text generation. We allow the discriminative net to leak its own high-level extracted features to the generative net to further help the guidance. The generator incorporates such informative signals into all generation steps through an additional Manager module, which takes the extracted features of current generated words and outputs a latent vector to guide the Worker module for next-word generation. Our extensive experiments on synthetic data and various real-world tasks with Turing test demonstrate that LeakGAN is highly effective in long text generation and also improves the performance in short text generation scenarios. More importantly, without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between Manager and Worker. read more

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Text Generation Chinese Poems LeakGAN BLEU-2 0.456 # 3
Text Generation COCO Captions LeakGAN BLEU-2 0.950 # 1
BLEU-3 0.880 # 1
BLEU-4 0.778 # 1
BLEU-5 0.686 # 1
Text Generation COCO Captions partGAN BLEU-2 0.910 # 2
BLEU-3 0.713 # 2
BLEU-4 O.753 # 5
BLEU-5 0.590 # 2
Text Generation EMNLP2017 WMT LeakGAN BLEU-2 0.956 # 1
BLEU-3 0.819 # 1
BLEU-4 0.627 # 1
BLEU-5 0.498 # 1

Methods


No methods listed for this paper. Add relevant methods here