Explore a comprehensive lecture on models with latent random variables in neural networks for natural language processing. Delve into the distinctions between generative and discriminative models, as well as deterministic and random variables. Gain insights into Variational Autoencoders, their architecture, and loss functions. Learn techniques for handling discrete latent variables, including the Gumbel-Softmax trick. Examine real-world applications of these concepts in NLP tasks, such as language modeling and semantic similarity. Engage with discussion questions to deepen understanding of tree-structured latent variables and their implications for NLP models.
Overview
Syllabus
Introduction
Discriminative vs generative
Observed vs latent variables
Quiz
Latent Variable Models
Types of latent random variables
Example
Loss Function
Variational inference
Reconstruction loss and kl regularizer
Regularized auto encoder
Regularized autoencoder
Learning the VAE
Reparameterization Trick
General
Language
VAE
Reparameterization
Motivation
Consistency
Semantic Similarity
Solutions
Free Bits
Weaken Decoder
Aggressive Inference Network
Handling Discrete latent variables
Discrete latent variables
Sampling discrete variables
Gumball softmax
Application examples
Discrete random variables
Tree structured latent variables
Discussion question
Taught by
Graham Neubig
Related Courses
-
CMU Advanced NLP 2022 - Latent Variable Models
-
Neural Nets for NLP - Models with Latent Random Variables
-
Neural Nets for NLP - Latent Random Variables
-
CMU Neural Nets for NLP - Models with Latent Random Variables
-
CMU Advanced NLP 2021 - Latent Variable Models
-
Neural Nets for NLP - Latent Variable Models
