N-GSLT: Natural Language Processing (Level 1)

Winter and Spring 2006

Course coordinator: Martin Volk (Stockholm University)

The aim of this course is to give a research-oriented overview of natural language processing focusing on the following two questions:

What are the standard methods used in the field?
What are the current research problems? [List collected by participants on Feb. 1, 2006]

The course is aimed both at students with limited knowledge of the field, for whom it is compulsory within GSLT, and at students with a more extensive background in natural language processing, who will be expected to take more active part in the discussion of current research. In this way, the course is meant to contribute to the common platform for students with different backgrounds within GSLT and NGSLT.

NB: The language for this course is English.

Part 1: Introductory Lectures (Göteborg)

	Date	Time	Room	Contents	Slides	Reading	Teacher
1	We 01. Feb.	8:15-10:00	C430	Introduction and overview	Introduction	J&M 1	Martin Volk
2	We 01. Feb.	10:15-12:00	C430	Words: morphology	Words	J&M 2-3	Lars Borin
3	Th 02. Feb.	8:15-10:00	C430	Syntax: PoS-Tagging	Tagging	J&M 8-9	Martin Volk
4	Th 02. Feb.	10:15-12:00	C430	Syntax: Parsing	Parsing Dan Jurafsky's Parsing slides	J&M 10-12	Martin Volk

5	Th 16. March	8:15-10:00	C430	Semantics: semantic analysis, disambiguation	Semantics	J&M 14-17	Torbjörn Lager
6	Th 16. March	10:15-12:00	C430	Pragmatics: discourse, generation, translation	Pragmatics	J&M 18, 20-21	Barbara Gawronska

Part 2: Distance Study Periods

The distance learning part of the course consists of four study periods of three weeks each:

Words [Mo 06. - Fr 24. February]
Coordinator: Lars Borin
Syntax [Mo 27. February - Fr 10. March, and Mo 20. - Fr 24. March]
Coordinator: Martin Volk
Semantics [Mo 27. March - Th 13. April]
Coordinator: Torbjörn Lager
Pragmatics [Tu 18. April - Fr 05. May]
Coordinator: Barbara Gawronska

During each of these study periods, students will be engaged in two kinds of activities:

A practical assignment, dealing with the implementation and/or evaluation of standard methods in the respective areas. (Students with different background knowledge may do different assignments here.)
A theoretical discussion of current research problems in the form of a chat session (or email discussion or video conference), based on the reading of recent articles and with an introduction by the respective teacher sent in advance by e-mail.

In addition to the practical exercises and online discussions, students will be expected to produce a term paper where they discuss a research problem of their own choice in relation to other areas of natural language processing. (``How does my research problem fit into the world of natural language processing?'')

Part 3: Closing Seminar (Stockholm)

The course will end with a seminar, where students will present their papers. The seminar will be held at Stockholm University, Monday-Tuesday, 29-30 May 2006.

Program (incl. term papers and discussants)

Course Requirements

In order to pass the course students must fulfill the following requirements:

Complete four practical assignments (one for each study period)
These assignments can be done individually or in groups of two (possibly three) students. Assignments should be completed by the end of each study period and the solutions made available on the group's web page. If an assignment is not completed on time, the group will be given an extra assignment which has to be completed before the end of the following study period. (The end of the following study period is also the deadline for assignments that have to be resubmitted.) Teachers are required to return assignments within one week.
Participate actively in the online discussions (chat or email or video seminars)
Students are expected to contribute to discussions in each of the four study periods (and should notify the responsible teacher if they are unable to do so). Students who fail to meet this requirement may be given another assignment instead.
Write and present a term paper (5-10 pages)
The set topic for this paper is to discuss the place of your own research problem within the larger field of NLP and to relate it to other problems and methods. (Other topics may be chosen after approval from the main responsible teacher.) Papers have to be finished by 22 May and will be discussed at the closing seminar in Stockholm 29-30 May, where each author has to make a short oral presentation. Each paper will be read and discussed by at least two other students.

Reading List

Introductory lectures:

J&M = Jurafsky, D. & Martin, J. H. (2000) Speech and Language Processing. Prentice-Hall.

Study period 1 (words):

Evans, Roger and Gerald Gazdar. 1996. DATR: A language for lexical knowledge representation. Computational Linguistics 22(2): 167-216.
Penton, David, Catherine Bow, Steven Bird and Baden Hughes. 2004. Toward a general model for linguistic paradigms. Proceedings of the EMELD Language Digitization Project 2004 Workshop on Linguistic Databases and Best Practice.

Study period 2 (syntax):

Eugene Charniak (1997) Statistical Techniques for Natural Language Parsing. AI Magazine.
Steven Abney (1997). Partial Parsing via Finite-State Cascades. J. of Natural Language Engineering, 2(4): 337-344.
Michael A. Covington, A fundamental Algorithm for Dependency Parsing, Proceedings of the 39th Annual ACM Southeast Conference, ed. John A. Miller and Jeffrey W. Smith, pp. 95-102, ACM, 2001

Study period 3 (semantics):

Blackburn, Patrick and Bos, Johan (2003) Computational Semantics, Theoria 18 No.46: 27-45, 2003
http://www.cogsci.ed.ac.uk/~jbos/pubs/theoria.pdf
Ng, Hwee Tou, & Zelle, John (1997). Corpus-Based Approaches to Semantic Interpretation in Natural Language Processing. AI Magazine, 18(4) (pp. 45 – 64). (Special Issue on Natural Language Processing).
http://www.aaai.org/Library/Magazine/Vol18/18-04/Papers/AIMag18-04-007.pdf

Study period 4 (pragmatics)

Last update on: Monday, 22. May 2006