Computational Linguistics
Administration
- Instructor:
- Shuly Wintner. Office
hours: Wednesday 13:00-14:00, Eshkol Tower 1217. Phone: (828)8180.
- Teaching assistant:
- Yael Cohen-Sygal
- Times:
- Spring 2002, Wednesday, 16:00-20:00. We will have an occasional
recitation ("tirgul"), probably on Wednesday 10:00-12:00.
- Place:
- Rabin 5002
- Prerequisites:
- Computational models (203.3510). Students without the required
background should
talk to the instructor prior to registration.
- Attendance:
- Optional but highly recommended.
- Grading:
- The final grade will be based on 4-6 home assignments
(approximately 33%) and two mid-term exams
(approximately 33% each). There will be no final exam.
- Mid-term exams:
- The first mid-term will cover the first half of the material and
will take place on 1 May or 8 May (during class time) The
second mid-term will cover the other half of the material and
will take place on 19 June (during class time).
- Home assignments:
- Approximately 5 home assignments will be handed out during the
semester. Submission is mandatory. Homework is to be done
independently and plagiarism will not be tolerated.
Content
- Textbook:
- There is no recommended textbook for this course, but some of the
material can be found in Speech and Language Processing, by Daniel Jurafsky and James H. Martin. It's a good book, albeit too shallow sometimes.
- Syllabus:
-
- Introduction
- Applications of natural language processing
- The structure of natural languages
- Different levels of language understanding: morphology, syntax and semantics
- Ambiguity
- Morphology
- Introduction to morphology: word structure
- Inflections and derivations
- Finite-state automata
- Finite-state transducers
- Syntax
- Introduction to syntax: the structure of natural languages
- Context-free grammars: grammars, forms, derivations, trees, languages
- Parsing: top-down, CYK algorithm, Earley algorithm, bottom-up chart parsing
- The complexity of natural language
- The limitations of CFGs
- Unification grammars: feature structures and unification
- Semantics
- Lexical semantics and WordNet
- Montague grammars
Announcements
- 15 January 2004
- Second midterm exam with its solution.
- 26 June 2002
-
Final grades are available here.
- 18 June 2002
-
Solution to home assignment 4 is available as Word .doc.
- 16 June 2002
- HW3 was graded. You can pick up your work at my office.
- 9 June 2002
- The second mid-term exam will take place during class time on June
19th (in the classroom). There will be no class on that day. Good luck.
- 9 June 2002
- This week's lecture will have two parts: the first will be an
ordinary lecture, which will include a conclusion of the
course. The second part will be a recitation of unification
grammars and will take place at the computer lab, room 571.
- 30 May 2002
- Deadline extension for home assignment 3. Please submit
by June 5th.
- 28 May 2002
- 10 points increase in your mid-term grade:
submit a proposal for a mid-term exam; if it's good, your mid-term
grade will increase by up to 10 points. Please submit your
proposal by June 12th.
- 28 May 2002
- Grades were updated.
The mid-term grades reflect a 10 point increase ("factor").
Please check your grades and verify that no errors were made.
- 23 May 2002
- Clarification: in HW3, please print all
derivation trees.
- 20 May 2002
- One-week deadline extension for home assignment 3. Please submit
by June 1st.
- 15 May 2002
- Instructions for using PCPATR are available in
PDF or Word .doc format.
- 12 May 2002
- A recitation (tirgul) will take place on
Wednesday, 15 May,
10:00-12:00, at the computer lab (room 565).
- 8 May 2002
- Mid-term grades are available.
The grades reflect a 10 point increase ("factor").
- 8 May 2002
- Home assignment 3 is available in
PDF or Word .doc format.
- 6 May 2002
-
The first mid-term exam is available as PDF or
Word .doc. Solutions are available in PDF or Word
.doc.
- 30 April 2002
-
Solution to home assignment 2 is available as PDF or Word .doc.
- 25 April 2002
- Submission of home assignment 2 is extended to Sunday. If you
submit it before Sunday 9:00am, there's a chance you'll have
it for the mid-term exam. Otherwise, you can submit by Sunday midnight.
- 23 April 2002
- The recitation (tirgul) of Wednesday, 24 April,
14:00-16:00, is moved again, back to room 344
(terrace building, third floor). Sorry for the mess.
- 22 April 2002
- Submission of home assignment 2 is extended to Thursday at 17:00.
- 22 April 2002
- The recitation (tirgul) of Wednesday, 24 April,
14:00-16:00, is moved to room 571.
- 21 April 2002
- A third recitation (tirgul) will take place on
Wednesday, 1 May,
18:00-20:00 (right after the exam), at the computer lab (room 571).
- 11 April 2002
- A second recitation (tirgul) will take place on Wednesday, 24 April,
14:00-16:00, at the computer lab (room 344, terrace building).
- 10 April 2002
- The first mid-term exam will take place on May 1st, during class.
- 10 April 2002
- The second home asignment is available.
- 8 April 2002
- A recitation (tirgul) will take place on Monday, 15 April, 14:00-16:00, at the
computer lab (room 571, near the computer center, main building).
- 8 April 2002
- Input for home assignment 1 is available in PDF or Word .doc format.
Note that some inputs are grammatical while others are not; your
progrma only has to cope with the grammatical inputs.
- 19 March 2002
- There's an error in one of the examples of home assignment 1. The
first analysis of "tagdil" should be
g.d.l+second person, singular, masculine
(rather than third person).
Copies of the slides
- Introduction
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript
- Morphology
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
- Finite-state technology
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
- Syntax
- Sorry, no slides available
- Context-free grammars
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
- Parsing
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
- Computational complexity of natural languages
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
- Unification grammars
-
in PDF format,
in PostScript format,
4-up PDF,
4-up PostScript.
Home assignments
- Morphological analysis of Hebrew verbs. Handed out: 20 March
2002. Due: by class time on 10 April 2002.
PDF. Input for the assignment is available in PDF or Word .doc format.
- Finite-state technology. Handed out: 10 April
2002. Due: by class time on 24 April 2002. Extended to 25
April at 17:00.
PDF or Word .doc format.
Solution is available as PDF or Word .doc.
- Context-free grammars and parsing. Handed out: 8 May
2002. Due: 25 May 2002. Deadline extended to June 1st..
PDF or Word .doc format.
- Unification grammars. Handed out: 5 June
2002. Due: 15 June 2002.
PDF or PostScript format. Solution is available as Word .doc.
Links
Computational Linguistics,
http://cs.haifa.ac.il/~shuly/teaching/02/nlp/
Maintained by
shuly@cs.haifa.ac.il
.
Last modified: Thu Jun 27 06:14:11 IDT 2002