Max Frenzel to Speak at GTC Japan 2018
On September 13th, Max Frenzel, a research scientist at Cogent Labs, will give a talk at GTC Japan 2018 about “Variational Autoencoders for NLP: Particular Difficulties, Recent Solutions, and Practical Applications” in Tokyo.
Title: Variational Autoencoders for NLP: Particular Difficulties, Recent Solutions, and Practical Applications
Date: 2018/9/13 (Thu.) 13:10-14:00
Session Type: Technical Session
Location: 3F Room 3-1
Overview: Deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have played a big role in the recent advancement of unsupervised learning. They can be used to compress data, reconstruct noisy or corrupted data, and allow us to perform sophisticated data manipulations. More subtly, they can uncover hidden concepts and relations in large amounts of unlabelled data. However, applying them to natural language has proven quite challenging. In this talk I will review the basic ideas behind VAEs, discuss why their application to NLP is particularly difficult, and introduce some more recent developments that have allowed us to overcome these challenges. Having covered the basic technical ideas, the second half of this talk will focus on a practical application, Cogent Labs’ natural language understanding engine Kaidoku, showcasing several business use cases.
Event name: GTC Japan 2018
Date: 2018/9/13 (Thu.) ~ 9/14 (Fri.)
Location: International Convention Center Pamir
3-13-1, Takanawa, Minato-ku, Toyko