Главная
Study mode:
on
1
Introduction
2
Types of prediction
3
Teacher forcing
4
Evaluation metrics
5
Structured prediction
6
Reminder
7
Globally normalized models
8
Sampling and Beam Search
9
Structured Perceptron
10
Global Structured Perceptron
11
Structured Training Pretraining
12
Hinge Loss
13
Cost Augmented Hinge Loss
14
Cost Over Sequences
15
Structured Hinge Loss
16
Label Smoothing vs Hinge Loss
17
Contrastive Learning
18
Teacher Forced
19
Selftraining
Description:
Explore structured learning algorithms in this advanced Natural Language Processing lecture from Carnegie Mellon University. Delve into reinforcement learning, minimum risk training, and the structured perceptron. Examine structured max-margin objectives and simple remedies to exposure bias. Learn about globally normalized models, sampling and beam search techniques, and various structured training approaches including hinge loss, cost-augmented hinge loss, and contrastive learning. Gain insights into teacher forcing, self-training, and evaluation metrics for structured prediction tasks in NLP.

CMU Advanced NLP: Structured Learning Algorithms

Graham Neubig
Add to list