Information extraction in the KELP framework

Robert Dale, Marc Tilbrook, Cecile Paris

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review


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 languageEnglish
Title of host publicationProceedings of the Seventh Australian Document Computing Symposium
EditorsJames Thom, Judy Kay
Place of PublicationSydney
PublisherSchool of Information Technologies, University of Sydney
Number of pages4
ISBN (Print)1864875259
Publication statusPublished - 2002
EventThe Seventh Australasian Document Computing Symposium (ADCS2002) - Sydney
Duration: 16 Dec 200216 Dec 2002


ConferenceThe Seventh Australasian Document Computing Symposium (ADCS2002)


  • information extraction
  • natural language generation
  • document personalisation


Dive into the research topics of 'Information extraction in the KELP framework'. Together they form a unique fingerprint.

Cite this