Chapters

• UNIX Corpus Tools (chapter )
• Overview of several selected corpora (chapter 5)
• The IMS Corpus Workbench (chapter 4.4)
• Introduction to probability and contingency tables (chapter 8)
• Information theory. Entropy, Mutual information (chapter 9).
• Hidden Markov Models and text-tagging. Forward-backward algorithm (chapter 10)
• Word-sense disambiguation. Clustering techniques (chapter )
• Computational Lexicography. (chapter )
• Statistical Parsing (chapter ).
• Information Extraction, MUC, other applications (chapter )
• Information Retrieval (chapter ).

The course provides both awareness of the theoretical issues in statistical language modelling and practical experience of applying it to corpora. After completing it, students should be in a position to understand and critique research papers in statistical computational linguistics. They should also be aware of the trade-offs involved in selecting statistical techniques for practical language engineering tasks.