arXiv (Cornell University) · 2017 · 90 citations · 17 references
ComputingComputer ScienceCurriculumComputer VisionMachine LearningNatural Language ProcessingDeep LearningGenerative ModelingLanguage ModelingNatural Language GenerationText GenerationConvolutional Neural NetworksCurriculum LearningGenerative Adversarial NetworksGenerative Image SynthesisLanguage GenerationRecurrent Neural NetworksSequence GenerationSynthetic Image Generation
Generative Adversarial Networks (GANs) have shown great promise recently in image generation. Training GANs for language generation has proven to be more difficult, because of the non-differentiable nature of generating text with recurrent neural networks. Consequently, past work has either resorted to pre-training with maximum-likelihood or used convolutional networks for generation. In this work, we show that recurrent neural networks can be trained to generate text with GANs from scratch using curriculum learning, by slowly teaching the model to generate sequences of increasing and variable length. We empirically show that our approach vastly improves the quality of generated sequences compared to a convolutional baseline.
17
Conditional Generative Adversarial Nets
Mehdi Mirza, Simon Osindero · arXiv (Cornell University) · 2014 · 8.9K citations · Full text
Yoshua Bengio, Jérôme Louradour, Ronan Collobert et al. · 2009 · 5K citations · Full text