C14: Introduction to Information Extraction

- from Natural Language Processing Aspect

Objectives

This module provides an overview of Information Extraction. After learning this module, students will have a general understanding about Information Extraction.

Description

This module provides a basic coverage of general issues related to Information Extraction. Major topics include:

Introduction of Information Extraction;
Regular Expressions;
Finite Automata in FASTUS;
Pushdown Automata and Context-free Grammars;
Limitation of Current Technology and Future Research;

It takes around 60 minutes to go through the required class notes and practice exercises. It is highly recommended that students read Chapter 3 of textbook Natural Language Processing for Online Applications - Text Retrieval, Extraction and Categorization, written by Peter Jackson and Isabelle Moulinier. The Web resources are also worth going through in order to get practical experience about Information Extraction.

Class Notes

(Required)

Information Extraction [flash] | [Windows Media] | [.ppt] | [.doc] | [.pdf]

Practice Exercise

Exercise: Introduction to Information Extraction
[Online Exercise]
Exercise and Answer Keys [.doc] | [.pdf]

Suggested Readings and Resources

In the Books

Chapter 3 of textbook Natural Language Processing for Online Applications Text Retrieval, Extraction and Categorization, written by Peter Jackson and Isabelle Moulinier, ISBN: 90-272-4989, Publisher: John Benjamins Publishing, 2002.

On the Web

Back to Modules