Skip to navigation | Skip to main content | Skip to footer
Menu
Menu

COMP30421: Natural Language Engineering (2007-2008)

This is an archived syllabus from 2007-2008

Natural Language Engineering
Level: 3
Credit rating: 10
Pre-requisites: No Pre-requisites
Co-requisites: No Co-requisites
Duration: 11 weeks
Lectures: 11 x 2 hours
Examples classes: none
Lecturers: Mary McGee Wood
Course lecturer: Mary McGee Wood

Additional staff: view all staff
Timetable
SemesterEventLocationDayTimeGroup
Sem 1 w1-5,7-12 Lecture LF15 Wed 10:00 - 12:00 -
Assessment Breakdown
Exam: 80%
Coursework: 20%
Lab: 0%
Degrees for which this unit is optional
  • Artificial Intelligence BSc (Hons)

Aims

The course unit aims to teach the principles and practice of natural language engineering:

To demonstrate how the essential components of NLE systems are built and modified.
To introduce the principal applications of NLE, including machine translation, information retrieval, information extraction, and the semantic web.
To explain the major challenges in processing large-scale, real-world natural language.
To align issues involved in NLE with related issues in software engineering and information systems.
To give students an understanding of what, realistically, NLE can and cannot hope to achieve, why, and why it matters.

Learning Outcomes

A student completing this course unit should:

Understand how to build a large-scale NLE system. ( A2, A5, B1 )
Know something about the principal practical applications of natural language engineering. ( A5 )
Understand the difficulties in NLE, and be able to predict, given an unfamiliar text, what problems it may cause. (A2, B3)
Be able to make an informed decision, given a previously unseen practical problem, as to which NLE techniques are likely to be worthwhile. ( B3 )
Evaluate the performance of NLE systems. (A2, A5, B3, C4, D4)
Be able to meet rigid short-term deadlines. ( D5 )

Assessment of Learning outcomes

Learning outcome 1, 2, 3 are assessed by examination and coursework, learning outcome 2 and 4 by examination, and 5 by exam and coursework learning outcome 6 by coursework.

Contribution to Programme Learning Outcomes

A2, A5, B1, B3, C4, D4, D5.

Syllabus

Introduction, motivation (1)


Techniques


Probabilistic grammars, N-grams, Hidden Markov Models (3)

Components


Overview, POS tagging, Stemming and morphology, Parsing, Word Sense Disambiguation (5)

Resources


Corpora and coding systems, Lexicons and ontologies, Standards (3)

Applications


Machine translation, Spoken Language Dialogue Systems, Information Retrieval, Information Extraction, Intelligent Tutoring Systems (5)

Conclusion (1)


Practical 1


POS tagging

Practical 2


Parsing

Practical 3


Word Sense Disambiguation

Practical 4


Machine Translation

Reading List

Core Text
Title: Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition (2nd edition)
Author: Jurafsky, Daniel and James H. Martin
ISBN: 9780135041963
Publisher: Pearson International
Edition:
Year: 2009
This is the course textbook.


Supplementary Text
Title: Foundations of Statistical Natural Language Processing
Author: Manning, Christopher D. and Hinrich Schutze
ISBN: 0262133601
Publisher: MIT Press
Edition:
Year: 2003
This is the secondary text to the course.