Abstract
In this paper, we describe some early steps in a new approach to information extraction. The aim of the kelp project is to combine a variety of natural language processing techniques so that we can extract useful elements of information from a collection of documents and then represent this information tailored t o t h e n e eds of a speciic user. Our focus here is on how we can build richly structured data objects by extracting information from web pagess as an example, we describe the extraction of information from web pages that describe l a p t o p c omputers. A principle goal of this work is the separation of diierent components of the information extraction task so as to increase portability.
Original language | English |
---|---|
Title of host publication | Proceedings of the Seventh Australian Document Computing Symposium |
Editors | James Thom, Judy Kay |
Place of Publication | Sydney |
Publisher | School of Information Technologies, University of Sydney |
Pages | 117-120 |
Number of pages | 4 |
ISBN (Print) | 1864875259 |
Publication status | Published - 2002 |
Event | The Seventh Australasian Document Computing Symposium (ADCS2002) - Sydney Duration: 16 Dec 2002 → 16 Dec 2002 |
Conference
Conference | The Seventh Australasian Document Computing Symposium (ADCS2002) |
---|---|
City | Sydney |
Period | 16/12/02 → 16/12/02 |
Keywords
- information extraction
- natural language generation
- document personalisation