Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Neural Nets for NLP - Structured Prediction Basics
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 A Prediction Problem
- 3 Types of Prediction
- 4 Why Call it "Structured" Prediction?
- 5 Many Varieties of Structured Prediction!
- 6 Sequence Labeling as
- 7 Sequence Labeling w
- 8 Why Model Interactions in Output? . Consistency is important!
- 9 A Tagger Considering Output Structure
- 10 Training Structured Models
- 11 Local Normalization and
- 12 The Structured Perceptron Algorithm . An extremely simple way of training (non-probabilistic) global models
- 13 Structured Perceptron Loss
- 14 Contrasting Perceptron and Global Normalization • Globally normalized probabilistic model
- 15 Structured Training and Pre-training
- 16 Cost-Augmented Decoding for Hamming Loss • Hamming loss is decomposable over each word • Solution: add a score - Cost to each incorrect choice during search
- 17 What's Wrong w/ Structured Hinge Loss?
