CMU Neural Nets for NLP - Structured Prediction Basics
Offered By: Graham Neubig via YouTube
Course Description
Overview
Syllabus
A Prediction Problem
Types of Prediction
Why Call it "Structured" Prediction?
Many Varieties of Structured Prediction!
Sequence Labeling w
Why Model Interactions in Output? . Consistency is important!
A Tagger Considering Output Structure movie
Training Structured Models
Local Normalization and
The Structured Perceptron Algorithm . An extremely simple way of training (non-probabilistic) global models . Find the one-best, and it's score is better than the correct answer adjust parameters to fix this
Contrasting Perceptron and Global Normalization
Structured Training and Pre-training
Hinge Loss for Any Classifier! We can swap cross-entropy for hinge loss anytime
Cost-augmented Hinge
Costs over Sequences
Cost-Augmented Decoding for Hamming Loss
Solution 1: Sample Mistakes in Training (Ross et al. 2010)
Taught by
Graham Neubig
Related Courses
Natural Language ProcessingColumbia University via Coursera Natural Language Processing
Stanford University via Coursera Introduction to Natural Language Processing
University of Michigan via Coursera moocTLH: Nuevos retos en las tecnologĂas del lenguaje humano
Universidad de Alicante via MirĂadax Natural Language Processing
Indian Institute of Technology, Kharagpur via Swayam