CS 5761 - Introduction to Natural Language Processing READING ASSIGNMENTS - SPRING 2004 All reading should be completed during the week it is assigned. Note that SLP refers to Speech and Language Processing by Jurafsky and Martin. Perl materials may be of your own choosing, although I make recommendations below. ======================================================================== Week 14 (ends May 2) : A Plan for Spam, by Paul Graham http://www.paulgraham.com/spam.html Better Bayesian Filtering, by Paul Graham http://www.paulgraham.com/better.html SpamCop: A Spam Classification & Organization Program, by Pantel and Lin http://www.isi.edu/~pantel/Download/Papers/aaai98.pdf ======================================================================== Week 13 (ends Apr 25) : no new reading ======================================================================== Week 12 (ends Apr 18) : SLP: Chapter 17 All students should try and use WordNet from command line Those working on Google project should try CPAN module WordNet::QueryData ======================================================================== Week 11 (ends Apr 11) : SLP: Chapter 16 ======================================================================== Week 10 (ends Apr 4) : SLP: Chapter 8 ======================================================================== Week 9 (ends Mar 28) : SLP: no new reading, review Chapters 1-6 for exam on Weds Mar 31. ======================================================================== Week 8 (ends Mar 14) : SLP: no new reading ======================================================================== Week 7 (ends Mar 7) : SLP: Chapter 6.6 - 6.7 ======================================================================== Week 6 (ends Feb 29) : SLP: Chapter 6.1 - 6.3 Get Google API http://www.google.com/apis ======================================================================== Week 5 (ends Feb 22) : SLP: Chapter 5.1 - 5.5 A Spelling Correction Program Based on a Noisy Channel Model, by Kernighan, Church, and Gale, 1990, Coling. ======================================================================== Week 4 (ends Feb 15) : SLP: Chapter 3 Perl: use of Text::English module (find at search.cpan.org) ======================================================================== Week 3 (ends Feb 8) : SLP: no new reading Perl: Review hashes and file handling. ======================================================================== Week 2 (ends Feb 1) : SLP: Chapter 2 Perl: Learn how to use regular expression matching and substitution. Learning Perl and Programming in Perl are very good introductions. When you become more expert, Mastering Regular Expressions in Perl is a good source. Experiment with hashes too. ======================================================================== Week 1 (ends Jan 25) : SLP: Chapter 1 Perl: Review introductory material from Learning Perl or Programming Perl. Make sure you are able to write simple Perl programs that use command line arguments and file i/o. ========================================================================