Adversarial network for natural language synthesis
Who is this presentation for?
- Data scientists, AI researchers, and university students
The key issue with generative tasks is about deciding what a good cost function should be. GAN introduces two networks to solve that. The generator network creates fake samples, and the discriminator network distinguishes them from real samples. GAN has been predominantly applied in image augmentation and is particularly good at generating continuous samples, but because of this, it can’t be used directly for text generation (as it’s sequence of discrete numbers.)
Rajib Biswas outlines the recent breakthroughs in applying adversarial networks for language generation such as SeqGAN (policy gradient reinforcement learning methods), LeakGAN (long text generation with leaked information), and a reparameterization trick for latent variables. You’ll learn about a variety of applications and tasks, including GAN for machine translation, GAN for dialogue generation, and GAN for style transfer, along with seeing a demonstration of language generation application with code.
- Familiarity with deep learning and natural language processing
What you'll learn
- Learn the state of the art in natural language generation and its practical applications
Rajib Biswas is a lead data scientist at Ericsson’s Global AI Accelerator. He has 10 years of industry experience in AI- and ML-based product development and research and has applied AI and ML to solve problems related to domains like finance, telecom, and consumer electronics. He holds a master’s in computer science from BITS-Pilani.
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
For media/analyst press inquires