Introduction to Natural Language Processing (CS 2731 / ISSP 2230), Fall 2003 |
|||
| Time: | M W 11:00-12:15 | Place | 5313 Sennott Square (NOTE CHANGE!) |
| Professor: | Diane Litman | Office Hours: | M 12:15-2:15 (5105 Sennott Square), Tu 10:00-12:00 (741 LRDC) |
| Email: | litman@cs.pitt.edu | Phone: | 412-624-8838 (Sennott Square); 412-624-1261 (LRDC) |
| TA: | Mihai Rotaru | Office Hours: | M W 9-11, Th 11-1 (5420 Sennot Square) |
| Email: | mrotaru@cs.pitt.edu | Phone: | 412-624-8462 |
This course provides an introduction to the theory and practice of natural language processing (NLP) - the creation of computer programs that can understand, generate, and learn natural language. We will use natural language understanding as a vehicle to introduce the three major subfields of NLP: syntax (which concerns itself with determining the structure of a sentence), semantics (which concerns itself with determining the explicit meaning of a single sentence), and pragmatics (which concerns itself with deriving the implicit meaning of a sentence when it is used in a specific discourse context). The course will introduce both knowledge-based and statistical approaches to NLP, illustrate the use of NLP techniques and tools in a variety of application areas, and provide insight into many open research problems.
Prerequisites: CS 1501
Speech and Language Processing by Jurafsky and Martin (errata).
For a selection of topics, we will also read
some current research papers. All students will be assigned a paper, and
will lead the portion of class
allotted to the discussion of that paper; the remaining students
will email questions, which will form the basis of the discussion.
Concepts taught in class will be reinforced
with assignments (both problem sets and programming), a project, and exams.
Each student will also lead a paper discussion, and will send email questions as well as participate in the other discussions.
Grade Basis: homeworks (35%), project (25%), exams (35%), leading
discussion & class participation (5%).
Late Penalty: For assignments that may be accepted late, the penalty is 10% per day up to 5 days including
Saturday, Sunday, and holidays. Assignments are due at the start of class.
Wednesdays 3-4: Natural
Language Processing Lab meetings, 5601 Sennott Square
Homework 1 (assigned 9/8, due 9/24); grades van den Bosch & Daelemans Peng et al.
Dickinson & Meurers (9/29)
Samuel et al. (10/1)
Homework 2 (assigned 10/1, due 10/20); grades
Prof. Rebecca Hwa guest lecture (10/6)
Johnson (10/8) NO MAKEUPS Moldovan et al. (10/27)
Cunningham et al. (10/29)
Shen (10/27), Kveton (10/27), and Bryant (10/29) discussions
Abney (11/3) Riloff and Wiebe (11/5) Barnden et al. (11/12)
Mohit discussion (11/12)
Diab and Resnik (11/19)
Singliar discussion (11/19)
Ng and Cardie (11/24)
NO MAKEUPS Assignments must be your own individual work, unless explicitly
stated otherwise.
You must do the work without undue help from other people, and you must not present material from resources such
as the Web, books, papers, code listings, and other people as your own. You may talk to each other about concepts and techniques,
but you must not discuss specific solutions or approaches to solutions.
Copying or paraphrasing someone's work, or permitting
your own work to be copied or paraphrased, even in part, is not
allowed and will result in an automatic grade of 0 for the assignment.
Classic NLP
programs
Requirements:
Announcements:
Syllabus (evolving and subject to change!):
Topic
Reading
Assignments
Course Overview and Administration (8/25)
Knowledge of Language (8/27, 9/3)
Ch 1
Send me your rankings of reading
list papers before September 3
Linguistic Background (optional)
Handouts (optional)
Regular Expressions and Automata (9/3, 9/8)
Ch 2
Reading
Assignments
Morphology and Finite State Transducers (9/10, 9/15, 9/17)
Ch 3
Vully discussion (9/15)
N-Grams (9/17,9/22)
Ch 6 (through 6.4)
Berfield discussion (9/22)
Part of Speech Tagging (9/24,9/29,10/1)
Ch 8
Ward (9/29) and Gupta (10/1) discussions
Context-Free Grammars (10/1,10/6,10/8)
Ch 9
Miller discussion (10/8)
Parsing with CFGs (10/13, 10/15)
Ch 10
Midterm Exam (Oct. 22)
Covers through Ch 10
Grades
Question Answering and Class Project (10/15, 10/20, 10/27)
Riloff & Thelen (10/27)
Project assigned (10/20)
Features and Unification (10/27) Ch 11
Farzan discussion (11/3)
Representing Meaning (10/29)
Ch 14
Semantic Analysis (11/3, 11/5)
Ch 15 (skip 15.2 though)
Polvichai discussion (11/5)
Lexical Semantics (11/5, 11/10, 11/12)
Ch 16
Project Preliminary Evaluation due (11/10;) results
Word Sense Disambiguation (11/12, 11/17)
Relevant parts of Ch 17 (through 17.2)
Homework 3 assigned (11/17); grades
Discourse (11/17, 11/19, 11/24)
Ch 18
Cois discussion (11/24)
Dialogue and Conversational Agents (12/1, 12/3)
Ch 19
Project Final Evaluation (12/5 - extension); results and progress; grades
Project Presentations (12/8)
NOTE: special class hours from 10:30-1:00
Project Reports Due (12/8); Remedia Results; Last year's Remedia Results
Final Exam (12/10)
Covers Ch 1, Ch 11, and from Ch 14 on.
Grades
Academic Integrity:
Interesting Links (besides resources
available from J&M):
Chapters 1 and 2:
Chapter 3:
AT&T Labs - Research Finite State Machine Library
Appelt and Israel's information extraction tutorial (IJCAI-99).
Allen's Dialogue Modeling for Spoken Language Systems tutorial (ACL Workshop 1997).
If you have a disability for which you are or may be requesting an accommodation, you are encouraged to contact both your instructor and Disability Resources and Services, 216 William Pitt Union, (412) 648-7890/(412) 383-7355 (TTY), as early as possible in the term. DRS will verify your disability and determine reasonable accomodations for this course.