Data Intensive Linguistics (P00864)

? Credit Points : 10 ? SCQF Level : 11 ? Acronym : INF-P-DIL

The course aims to help the student understand some of the factors involved with modelling natural language phenomena (such as parsing, word sense disambiguation, part-of-speech tagging etc) from a mainly statistical perspective.

Entry Requirements

? Pre-requisites : This course involves some programming (suitable languages include Perl, C, and/or lisp), a moderate understanding of probability theory and some exposure to natural language processing. LFD1 and ICL are strongly recommended.

Subject Areas

Home subject area

Artificial Intelligence, (School of Informatics, Schedule O)

Delivery Information

? Normal year taken : Postgraduate

? Delivery Period : Semester 2 (Blocks 3-4)

? Contact Teaching Time : 2 hour(s) per week for 10 weeks

First Class Information

Date	Start	End	Room	Area	Additional Information
09/01/2006	14:00	15:00			Forrest Hill, Room A9/11

All of the following classes

Type	Day	Start	End	Area
Lecture	Monday	14:00	14:50	Central
Lecture	Thursday	14:00	14:50	Central

Summary of Intended Learning Outcomes

It is anticipated that students who successfully complete this course will be able to:
-Describe the main algorthms used in statistical natural language processing.
-Discuss the factors involved with processing noisy data sets.
-Understand how to construct systems using small quantities of labelled data.
-Understand the nature of existing language datasets. Demonstrate an understanding of how to apply techniques from statistical natural language processing to natural language problems.
-Critically understand research literature in the field.