Extracting significant words from corpora for ontology extraction

Dileep Damle, Victoria Uren

Research output: Chapter in Book/Published conference outputConference publication

Abstract

We show a new method for term extraction from a domain relevant corpus using natural language processing for the purposes of semi-automatic ontology learning. Literature shows that topical words occur in bursts. We find that the ranking of extracted terms is insensitive to the choice of population model, but calculating frequencies relative to the burst size rather than the document length in words yields significantly different results.
Original languageEnglish
Title of host publicationProceedings of the 3rd international conference on knowledge capture - K-CAP '05
Place of PublicationNew York, NY (US)
PublisherACM
Pages187-188
Number of pages2
ISBN (Print)1-59593-163-5
DOIs
Publication statusPublished - 2 Oct 2005
Event3rd international conference on Knowledge capture - Alberta, Canada
Duration: 2 Oct 20055 Oct 2005

Conference

Conference3rd international conference on Knowledge capture
Abbreviated titleK-CAP'05
Country/TerritoryCanada
CityAlberta
Period2/10/055/10/05

Fingerprint

Dive into the research topics of 'Extracting significant words from corpora for ontology extraction'. Together they form a unique fingerprint.

Cite this