Abstract
| 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 |
Fingerprint
Keywords
- information extraction
- natural language generation
- document personalisation
Cite this
}
Information extraction in the KELP framework. / Dale, Robert; Tilbrook, Marc; Paris, Cecile.
Proceedings of the Seventh Australian Document Computing Symposium. ed. / James Thom; Judy Kay. Sydney : School of Information Technologies, University of Sydney, 2002. p. 117-120.Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › Research › peer-review
TY - GEN
T1 - Information extraction in the KELP framework
AU - Dale, Robert
AU - Tilbrook, Marc
AU - Paris, Cecile
PY - 2002
Y1 - 2002
N2 - 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.
AB - 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.
KW - information extraction
KW - natural language generation
KW - document personalisation
M3 - Conference proceeding contribution
SN - 1864875259
SP - 117
EP - 120
BT - Proceedings of the Seventh Australian Document Computing Symposium
A2 - Thom, James
A2 - Kay, Judy
PB - School of Information Technologies, University of Sydney
CY - Sydney
ER -