CS114 Home

Course Description
This course provides a comprehensive introduction to the theoretical foundations and algorithmic techniques for enabling computers  to process and understand natural language in any form, from naturally occurring speech, to webpages, books, andscientific articles. This course will be of interest to students of artificial intelligence, algorithms, linguistics, and the computational modeling of language comprehension and production.

Course Details

Time: Tuesday and Friday 11:00-12:20 pm

Location: Volen 106

Professor: James Pustejovsky

258 Volen Center


Office Hours: MW 2:30-4:00 p.m.

Teaching Assistant: John Vogel

110 Volen Center


Office Hours: W 10 AM - Noon or by appointment

Required Textbooks

Speech and Language Processing (Second Edition), by Daniel Jurafsky and James H. Martin
Natural Language Processing with Python, by Steven Bird, Ewan Klein, and Edward Loper

Grading Information

Your grade for this class is based on several problem sets, in-class quizzes, and class participation.  The breakdown is as follows:
  • Programming Assignments - 40%
  • In-class Quizzes - 15% each
  • Final Exam - 20%
  • Class Participation - 10%
Late Policy: Problem sets are due at the beginning of class unless otherwise stated.  For each day your assignment is late, you will lose 5%.  No extensions will be granted on the due date without a documented reason.

News Items

  • Quiz 3 Topics
    Topics for the final quiz will include:
    1. FSAs for language analysis (simple example)
    2. N-grams and how they can be used
    3. CFG and syntactic ambiguity 
    4. Learning theory (general)
    5. Classification using naive Bayes and decision trees
    6. What's entropy?

    Remember, it will be much shorter!!!
    Posted Apr 29, 2012, 10:25 AM by James Pustejovsky
  • Quiz 2 Topics
    Don't forget, there is an in-class quiz on Tuesday, April 3. Questions will be drawn from the following areas:
    1. Syntax and grammar phrase structure, generating a sentence from a grammar, overgeneration
    2. Parsing syntactic structures: Early algorithm
    3. Word sense: WordNet, computing similarity of senses, etc. 
    4. Entropy and simply information theoretic concepts
    5. Semantic Roles
    It will be MUCH shorter than the 1st quiz. Good luck studying. If you have questions, email me this weekend.

    Posted Mar 31, 2012, 9:36 AM by James Pustejovsky
Showing posts 1 - 2 of 11. View more »

Recent Files

  • Norvig-ChomskyTwoCultures.html   67k - Jan 28, 2012, 1:53 PM by James Pustejovsky (v2)
    ‎Peter Norvig, "On Chomsky and the Two Cultures of Statistical Learning" May 2011‎
  • LxForEveryone_SyntaxCh7.pdf   7453k - Jan 28, 2012, 10:07 AM by James Pustejovsky (v1)
    ‎Syntax: Heads and Phrases‎
  • Meteer and Iyer   0k - Jan 21, 2012, 9:11 AM by James Pustejovsky (v1)
    ‎Meteer, M. and R. Iyer (1996) Modelng Conversational Speech for Speech Recognition, in Proceedings of EMNLP.‎
  • Why your computer Doesn't Understand you   0k - Jan 19, 2012, 12:59 PM by James Pustejovsky (v1)
    ‎Interview in Brandeis Journal Catalyst, with James Pustejovsky on Computational Linguistics.‎
Showing 4 files from page Readings.