Главная
Study mode:
on
1
Introduction
2
Types of Variables
3
Latent Variable Models
4
Loss Function
5
Variational inference
6
Regularized Autoencoder
7
Sampling
8
ancestral sampling
9
conditioned language models
10
Motivation for latent variables
11
Training VAEs
12
Aggressive inference network learning
13
Latent variables
14
Discrete latent variables
15
Reparameterization
16
Random Sampling
17
Reparameterization Trick
18
Gumball Softmax
19
Gumball Function
20
Application Examples
Description:
Explore latent variable models in advanced natural language processing through this comprehensive lecture. Delve into generative vs. discriminative models, deterministic vs. random variables, and variational autoencoders. Learn about handling discrete latent variables, examine examples of variational autoencoders in NLP, and understand the difference between learning features and learning structure. Cover topics such as loss functions, variational inference, regularized autoencoders, sampling techniques, and the motivation behind using latent variables. Discover training methods for VAEs, including aggressive inference network learning, and explore the reparameterization trick and Gumbel-Softmax function. Gain insights into practical applications of these concepts in NLP tasks.

CMU Advanced NLP 2022 - Latent Variable Models

Graham Neubig
Add to list
0:00 / 0:00