Adversarial network for natural language synthesis
The key issue with generative task is about deciding what a good cost function should be? GAN(Generative Adversarial Networks) introduces two networks to solve that. The generator network creates fake samples, and Discriminator network distinguishes them from real samples.
GAN has been predominantly applied in image augmentation. GAN is particularly good at generating continuous samples. Due to this reason, it can’t be used directly for text generation (as it's sequence of discrete numbers.).
This talk will cover the recent breakthroughs in applying adversarial networks for language generation.
Outline/Structure of the Talk
Major developments in Adversarial network for text generation:
The talk will focus on the following recent advancements in GAN for natural language generation tasks.
- SeqGAN: Policy gradient Reinforcement learning methods
- LeakGAN: Long text generation with leaked information
- Re-parameterization trick for latent variables
Application: Following tasks will be covered in next section :
- GAN for Machine Translation
- GAN for Dialogue Generation
- GAN for Style transfer
Demo : demonstration of language generation application with code.
Learn state of the art in natural language generation and it's practical application .
Data Scientist, Researcher, Students
Prerequisites for Attendees
Audience basic familiarity with deep learning and natural language processing.