Example-based models of language

Prerequisites

Requirements: Basic programming skills (proficiency in some scripting language suffices)
This course is only open to students admitted to the research master Language and Communication. Admission of students from other (research) masters and PhD students is subject to approval by the programme coordinator (please contact

Contents

Example-based or memory-based language processing (MBLP) is a computational approach to language processing based on exemplar storage during learning and analogical reasoning during processing. From a cognitive perspective, the approach is attractive as a model for human language processing because it does not make any assumptions about the way abstractions are shaped, nor any a priori distinction between regular and exceptional exemplars, allowing it to explain fluidity of linguistic categories, and both regularization and irregularization in processing. Schema-like behavior and the emergence of categories can be explained in MBLP as by-products of analogical reasoning over exemplars in memory. This course discusses the theory and practice of memory-based language processing, following the tutorial structure of the book used for the course.

Objectives

After completion of the course the student has a general understanding of the concept of example-based language modeling, both from the computational perspective (how does it work) and its theoretical implications (how does it tie in with other linguistic and cognitive theories on example-driven learning and processing, and theories of memory). The student is able to apply existing memory-based learning software to linguistic problems and report about these experiments.

Teaching method

The course is taught as a series of lectures combined with practical assignments featuring simple models. Use will be made of various open source software packages as referred to from the book: TiMBL, MBT, which are available both as software packages (for the computationally advanced students) and as webservices.

Teaching hours/week

2

Examination

30% of the final grade is determined by a mid-term report at the end of the third period describing a small-scale study in a research paper. At the end of the fourth period a larger end assignment is performed also leading to a research paper; the end assignment determines 70% of the final grade.

Literature

Daelemans, W., and Van den Bosch, A. (2005). Memory-based language processing. Cambridge, UK: Cambridge University Press.

Information

Prof. A.P.J. van den Bosch

Course ID
LET-REMA-LCEX07
Credits
6 ec
Level
Research Master
Scheduled
Period 3 and 4

Lecturer

Included in

  • Research Master Language and Communication