Главная
Study mode:
on
1
Introduction
2
Discriminative vs generative models
3
Types of variables
4
Loss function
5
Two tasks
6
Bias and variance
7
Evidence lower bound
8
Procedural training
9
Questions
10
Learning the VAE
11
Generating Sentences
12
Problems
13
kl divergence annealing
14
Free bits
15
Weaken the decoder
16
Aggressive inference network learning
17
Standard variational autoencoder
18
What are discrete latent variables
19
Method 1 Sampling
20
Method 2 Sampling
21
Method 2 Reparameterization
Description:
Explore latent variable models in advanced natural language processing through this comprehensive lecture from CMU's CS 11-711 course. Delve into the distinctions between generative and discriminative models, as well as deterministic and random variables. Gain insights into Variational Autoencoders (VAEs) and their applications in NLP, including techniques for handling discrete latent variables. Examine the trade-offs between learning features and learning structure. Cover topics such as evidence lower bound, procedural training, KL divergence annealing, and aggressive inference network learning. Understand sampling methods and reparameterization for discrete latent variables, equipping you with advanced knowledge for implementing sophisticated NLP models.

CMU Advanced NLP 2021 - Latent Variable Models

Graham Neubig
Add to list