Explore adversarial methods in neural networks for natural language processing in this lecture from CMU's CS 11-747 course. Delve into generative adversarial networks, adversarial feature learning, and adversarial attacks and training. Learn about generative models, distribution matching, GANs for text, domain-invariant representations, multitask learning, and unsupervised machine translation. Discover techniques for adversarial robustness, including adversarial examples and training methods. Gain insights into the challenges and applications of adversarial approaches in NLP tasks.
Overview
Syllabus
Adversarial Methods
generative models
nonlatent models
examples
models
training method
distribution matching
pseudocode
gans good
gans for text
latent variables
training
text stabilization
discrimination over soft max
Adversarial feature learning
Domain invariant representations
Language variant representations
Multitask learning
Professor forcing
Unsupervised distribution matching
Unsupervised machine translation
Adversarial robustness
Adversarial example
Adversarial training
Taught by
Graham Neubig
Related Courses
-
Advanced NLP: Adversarial Methods for Text
-
CMU Advanced NLP 2021 - Adversarial Learning
-
Neural Nets for NLP 2017 - Adversarial Learning
-
Keras Deep Learning & Generative Adversarial Networks (GAN)
-
Generative AI and LLMs: Architecture and Data Preparation
-
Advanced Generative Adversarial Networks (GANs)
