Vorlesung:
Lecturer: Dietrich Klakow
Location: Seminarraum Building C7 2
Time: Fr 8.30 - 10 Uhr
Starts: 23.04.2010
Geeignet für: M.Sc.

Exercises:
Tutor: Grzegorz Chrupała
Location and Time : Friday 12:00-14:00
Starts: May 7

How does a search engine find the right web page? How can information be extracted from e-mails. The lecture will introduce statistical methods to process natural language. Also common themes like the design of classifiers will be treated.
The lecture covers the following topics:

language processing: basic terms
mathematical foundations
word sense disambiguation
part-of-speech tagging
named-entity recognition
statistical methods in information retrieval
text classification

Slides
Chapter 1: Overview pdf
Chapter 2 Natural Language pdf
Chapter 3 Basics of Language Modeling pdf
Chapter 4 Entropy pdf
Chapter 5 Backing-Off Language Models pdf
Chapter 6 Text Classification pdf
Chapter 7 Word Sense Disambiguation pdf
Chapter 8 Information Retrieval pdf
Chapter 9 Maximum Entropy Models pdf
Chapter 10 Conditonal Random Fields pdf

Exercises
Exercise 1
Exercise 2
Exercise 3
Exercise 4
Exercise 5
Exercise 6
Exercise 7
Exercise 8
Exercise 9
Exercise 10