LECTURE 43: EVALUATION METRICS

• Objectives:
  
  
  • Human Performance
    
    
  • Machine Performance
    
    
  • Automated Scoring: String Alignment
    
    
  • Precision and Recall

This lecture uses material from the instructor's notes. Most NLP books contain information about scoring. A good resource is:

D. Jurafsky and J.H. Martin, SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition, Prentice-Hall, ISBN: 0-13-095069-6, 2000.