Introduction to Natural Language Processing

This course teaches students basic skills needed to tackle analysis and generation tasks in natural language processing (NLP) with knowledge-based methods. Starting from fundamentals of linguistics and empirical methods, the course introduces rule-based and basic statistical techniques. The application of these techniques is exemplified for fundamental NLP tasks, including text segmentation, syntactic parsing, and entity recognition. Students learn to design, implement, and evaluate respective NLP methods, both theoretically and in practical assignments. Besides the topical content, the course aims to educate students in how to conduct data-driven scientific experiments. 

• Overview of Natural Language Processing
• Basics of Linguistics
• NLP using Rules
• NLP using Lexicons
• Basics of Empirical Methods
• NLP using Grammars
• NLP using Language Models
• NLP using Clustering
• Practical Issues

• Basics of statistics
• Knowledge of programming, ideally Python

• Daniel Jurafsky and James H. Martin. 2009. Speech and Language Processing: An Introduction to Natural Language Processing, Speech Recognition, and Computational Linguistics. Prentice-Hall, 2nd edition. Free draft of third edition: Speech and Language Processing

Lecture slides

• Part I – Overview (slides)
• Part II – Basics of Linguistics (slides)
• Part III – NLP using Rules (slides)
• Part IV – NLP using Lexicons (slides)
• Part V – Basics of Empirical Methods (slides)
• Part VI – NLP using Grammars  (regex slides last year, CFG slides last year)
• Part VII – NLP using Language Models (slides last year)
• Part VIII – NLP using Clustering (new)
• Part IX – Practical Issues (slides last year)

Organizational information

• General course Information (slides)