CS578 Natural Language Processing

---

Semester    :  Fall 2006
Instructor  : Ilyas Cicekli ( Office: EA504,    Tel: 290-1589,    Email:  ilyas@cs.bilkent.edu.tr )
Office Hours : Wednesday 9:30-11:30
Class Hours  : Wednesday 11:40-12:30, Friday 8:40-10:30 (EA502)

But, I am planning to have 3-hour course on Friday 8:40-11:30 if there is no problem with the students.

---

Text Book

1. Daniel Jurafsky, and James H. Martin, "Speech and Language Processing",  Prentice Hall,  2000.

Other References

1. James Allen, "Natural Language Understanding", Second edition, The Benjamin/Cumings Publishing Company Inc., 1995.
2. Christopher D. Manning, and Hinrich Schutze, "Foundations of Statistical Natural Language Processing", The MIT Press, 1999.
3. Gerald Gazdar and Chris Mellish, "Natural Language Processing in Prolog", Addison Wesley, 1989.
4. Fernando C.N. Pereira, and Stuart M. Shieber, "Prolog and Natural Language Analysis", CSLI Lecture Notes, 1987.
5. Survey of the State of the Art in Human Language Technology for a good overview of the field.

---

Grading

Project : 60%

Final : 30%

Homeworks+Attendance : 10%

---

Project

Each student will do a survey in an advanced topic in NLP field, and a computational work as a project. You should read at least 2-3 major papers in that field, and prepare a professionally written paper (in the format of a conference or journal paper) for your project.  At the end of semester, you will return your paper together with the copies of the major papers that you read and you will present your project.

· Possible Project Topics

· Presentation Schedule

---

Homeworks

---

Course Outline:

• Introduction/Overview of NLP (Chapter 1 from Jurafsky’s book)
• Morphological Processing (Chapters 2 and 3 from Jurafsky’s book)
• Statistical Methods (Chapter 5 and 6 from Jurafsky’s book, and some other material from other books)
• Part-of-Speech Tagging (Chapter 8 from Jurafsky’s book)
• Parsing Algorithms for Context-Free Languages (Chapters 9 and 10 from Jurafsky’s book)
• Features and Augmented Grammars (Chapter 11 from Jurafsky’s book)
• Lexicalized and Probabilistic Parsing (Chapter 12 from Jurafsky’s book)
• Semantic Analysis (Chapter 14 and 15 from Jurafsky’s book)
• Lexical Semantics and Word Sense Disambiguation (Chapter 16 and 17 from Jurafsky’s book)
• Discourse (Chapter 18 from Jurafsky’s book)
• Natural Language Generation (Chapter 20 from Jurafsky’s book)
• Machine Translation (Chapter 21 from Jurafsky’s book)

---

Miscellaneous NLP Information

1. Survey of the State of the Art in Human Language Technology

---

Lecture Notes:

• lec00-outline
• lec01-overview
• lec02-regexp
• lec03-morpohology
• lec03-morpohology-A1-pckimmo
• lec03-morpohology-A2-englex
• lec03-morpohology-A3-examples
• lec04-statistics
• lec05-pos
• lec06-CFGParsing
• lec07-Features
• lec08-PCFG
• lec09-semantics
• lec10-lexicalsemantics
• lec11-gen1
• lec11-gen2
• lec11-mt

---

Announcements:

· Final Exam is on December 28, 2006, Time: 9:00, Location: our classroom (EA502), a closed book exam.

· Project demos are on December 28 and 29 in my office.

o If you are going to make your demo on different day, you have to make an appointment for that day.

o On your demo day, be ready to give your software to me.

· Due date for your final reports is also December 29.

· At the end of semester, you should hand in:

o A hard copy of your project paper.

o A zip file (maybe in a CD) containing

§ A soft copy of your project report

§ Power-point slides of your presentation

§ Soft copies of your major references

§ Your software and related documents (source codes, corpus, …)

---

Current Grades:

Final Grades

---