Hack Session: Synthetic Text Data Generation using Recurrent Neural Networks (RNN)

Nov 15, 2019

12:35

Auditorium 3

55 minutes

Natural Language Processing

Learn about an interesting use case where Deep Learning (DL) techniques are being utilized to generate data along with some interesting architectures for the same. In this hack session, we will cover the motivations behind utilizing such a pipeline to develop a robust pipeline for handling handwritten text. The session would take you through a hands-on journey covering the following aspects:

  • A quick overview of RNNs and different DL architectures for such a use case
  • Brief introduction¬†to some interesting research into this domain
  • Hands-on code walkthrough to prepare a simple DL model to generate text
  • Model fine-tuning and results

 

Key Takeaways:

  • Understanding the use of DL models to generate data (this talk is not about GANs!)
  • Building a DL model to generate synthetic handwritten text to solve real world problems

 

Check out the below video to know more about the session.

  • Raghav Bali

    Senior Data Scientist

    UnitedHealth Group

Copyright 2019 Analytics Vidhya. All rights reserved