COMP5410M
Language
15 credits

Taught Semester 2 View Timetable

Year running 2005/06

This module is not approved as an Elective

Objectives
On completion of this module, students should be able to:
* demonstrate an understanding of the theory and terminology of empirical modelling of natural language;
* use algorithms, resources and techniques for implementing NLP systems;
* apply machine learning and reasoning techniques to NLP;
* demonstrate familiarity with some of the main language engineering application areas;
* appreciate differences between individual languages;
* apply some standard techniques to a variety of languages.

Syllabus
Short introduction to linguistic theory and terminology. Algorithms and techniques for computer-assisted text processing; including algorithms for syntactic, semantic and discourse analysis and covering some of the main problems in these areas (tagging, parsing, word sense disambiguation, anaphora resolution). The focus will be on data-driven corpus-based and machine-learning approaches, although some reasoning/KR approaches will also be included. Evaluation methodologies and problems, linked to human performance in these areas. Performance of algorithms for languages other than English. Resources: Corpus design, annotation and analysis; Machine-Readable dictionaries and lexical databases. Non-English resources. Applications: Current applications for NLP systems and Language Engineering with a focus on applications relevant to cognitive systems (dialogues systems, NLP in robotics).

Teaching methods
Lectures: 20 x 1 hour;
Laboratory sessions: 2 x 2 hours.

Private study
Taught session preparation: 16 hours;
Taught session follow-up: 32 hours;
Self-directed study: 53 hours;
Summative assessment activities: 25 hours.

Methods of assessment
Exam: 1 paper, 2 hours, 60%, open notes;
Departmental assessment: 40%.

Reading list
The reading list is available from the Library website

Last updated: 23/03/2005

Disclaimer

Undergraduate module catalogue | Taught Postgraduate module catalogue

Errors, omissions, failed links etc should be notified to the Catalogue Team.