06-11223 Natural Language Processing & Applications

General Information

The tutor for this module is Dr. Mark Lee.

Mark has an office hour on Tuesdays at 11 am. Any student is welcome to see him then to discuss the module. You can also email.

The module will be taught by lectures on Monday between 2 pm and 4 pm in the LR UG5 in the Learning Centre (opposite Computer Science)

The official module page is at (06-11223) Natural Language Processing & Applications . Please check this for the formal information on assessment etc.

The standard text book for Natural Language Processing is
Speech and Language Processing
Jurafsky, D. & Martin, J.H.
Prentice Hall, 2000

It isn't a perfect match for the module content but will support the material. I'll also provide material to read during the module.

Continuous Assessment

The continuous assessment for this module is available here.

Results for continuous assessment are available here.

There is a page of useful data and NLP resources to support the coursework here

Module Content

Week Topic
1 Introduction to module
The lecture covered:
  • Module Structure
  • Assessment
  • An introduction to NLP
  • Sentiment Analysis as an example application

The lecture slides are available here
except I updated the schedule & assessment from last year. The update is here.

2 Word Sense Disambiguation
The lecture covered:
  • Dictionary Definitions
  • Word Sense Disambiguation

The lecture slides are available here
I also gave out some reading - Adam Kilgarriff's "I don't believe in word senses" paper. This is available here.

3
There was no lecture in Week 3!
4 Syntax & Parsing 1
The lecture covered:
  • English Syntax
  • Context Free Grammars
  • Parsing
  • CKY Algorithm

The lecture slides are available here
The additional classwork is available here

4 Syntax & Parsing 2
The lecture covered:
  • POS Tagging
  • Probabilistic Context Free Grammars
  • Natural Language learning

The lecture slides for the first part are available here
The lecture slides for the second part are available here
These slides were originally written by David Brooks

5Semantics The lecture covered:
  • Semantics Issues
  • First Order Predicate Logic
  • Discourse Representation Theory

The lecture slides are available here
I recommended reading Jan van Eijck's paper on DRT. It's available here The full reference is
Jan van Eijck (2006) "Discourse Representation Theory" in Encyclopedia of Language and Linguistics, Elsevier. Volume 3, pp. 660--669.

6 Discourse
The lecture covered:
  • Discourse Issues
  • Pronoun Co-reference
  • Rhetorical Structure Theory

The lecture slides are available here

A worked example of centuring theory is available here

7 Information Extraction & Retrieval The lecture covered:
  • Information Extraction
  • Information Retrieval

The lecture slides are available here for part a (IE)
and here for part b (IR)

8 Question Answering The lecture covered:
  • TREC
  • Question Answering
  • Textual Inference

The lecture slides are available here
The following link is a paper by Harabagiu, Moldovan et al. here
The full reference is
Sandra Harabagiu and Dan Moldovan and Christine Clark and Mitchell Bowden and Andrew Hickl and Patrick Wang (2005)
Employing Two Question Answering Systems in TREC-2005
In TREC Proceedings

Page updated by mgl 15th January 2011.