619-594-0252
619-594-4877
Syllabus and Course Materials
Lectures
- The "Empirical" Approach to Linguistics: Lecture 1
- Introduction to Probability: Lecture 2
- Expectation and Entropy: Lecture 3
- Ngram models and Smoothing: Lecture 4
- Discounting
- Cross-entropy
- A Simple HMM tagger
- Viterbi algorithm for Speech
- Baum-Welch algorithm
- Parsing
- Probabilistic CFGs
- Earley Algorithm and Cubic Time
Homework
Useful Websites
- Foundations of Statistical NLP website Jurafsky and Martin Textbook website
- Great Computational Linguistics Site at Tokushima U. Links to many useful sites!
- Linguistics, Natural Language, and Computational Linguistics Meta-Index
- Science archives; Search CS for Comp Ling articles.
Outside Reading
- CMU Statistical Toolkit documentation
- Manning and Klein: Grammar Induction
- Sense Disambiguation: Yarowsky
- Clustering: Lee's Thesis
- Bigram Statistical Parsing: Collins
- Three Bilexical Models: Collins
- CFG parsing and Words: Charniak
- Immediate Head Parsing: Charniak
- Cubic Time Dependency Parsing: Eisner
Jean Mark Gawron gawron@mail.sdsu.edu SDSU, 5900 Campanile Drive, San Diego, CA 92182-7717
Last modified: Tue Aug 22 15:39:48 2000