CSC 248/448  Home Page   

Fall 2003


This pages gives pointers to all the handouts and resources for the course. There is a great website of resources that is a companion to the Manning and Schutze text.


A description of the course is found in the Course Handout. A syllabus will be available shortly.



Lecture 1: Overview and Key Concepts

Lecture 2: A Whirlwind Tour of Probability

Lecture 3: Estimating Probability Distributions

Lecture 4: Estimating with Hold Outs

Lecture 5: More on Estimation

Lecture 6: Entropy and Information Theory

Lecture 7: Basic Automata Models

Lecture 8: Tagging Applications

Lecture 9: Searching HMM Models

Lecture 10: Learning with Hidden Data: The EM Algorithm

Lecture 11: Training HMMs

Lecture 12: Approaches to Speech Recognition

Lecture 13: Signal Processing for Speech-

Lecture 14: Building Code Books

Lecture 15: Search and Training for Large Vocabulary Speech Recognition

Lecture 16: Simple Alignment Models

Lecture 17: Using unordered Contexts

Lecture 18: Information Retrieval

Lecture 19: Probabilistic Context Free Grammars

Lectures 20 and 21: Machine Translation (these are notes from Kevin Knight the first 12 sections review work covered earlier in the course. MT starts with section 13)

Lecture 22: Effective CFG Models


Assignment 1, Due September 16. There are two test corpora for the assignment. Here are assignment one solutions.

Assignment 2, Due October 2 . The test corpora can be found at

               Here are assignment two solutions.

Assignment 3: Due November 4th.  Here is the data file.

Assignment 4: Due November 25th. Here is the training data.

Makeup Assignment, Due December 9th at start of class. No late assignments accepted.


A copy of the midterm from last time is