Building hybrid knowledge representations from text

J. Meyer, R. Dale

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

2 Citations (Scopus)

Abstract

A significant obstacle to the development of intelligent natural language processing systems is the lack of rich knowledge bases containing representations of world knowledge. For experimental systems it is common practice to construct small knowledge bases by hand; however, this approach does not scale well to large systems. An alternative is to attempt to extract the desired information from existing knowledge sources intended for human consumption; however, attempts to construct broad-coverage knowledge bases using in-depth analysis have met with limited success. In this paper we present some preliminary work on an alternative approach that involves using shallow processing techniques to build a hybrid knowledge representation that stores information in a partially analysed form.

Original languageEnglish
Title of host publicationProceedings - 23rd Australasian Computer Science Conference, ACSC 2000
Place of PublicationCanberra
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages158-165
Number of pages8
ISBN (Print)076950518X
DOIs
Publication statusPublished - 2000
Event23rd Australasian Computer Science Conference, ACSC 2000 - Canberra, Australia
Duration: 31 Jan 20003 Feb 2000

Other

Other23rd Australasian Computer Science Conference, ACSC 2000
CountryAustralia
CityCanberra
Period31/01/003/02/00

Fingerprint Dive into the research topics of 'Building hybrid knowledge representations from text'. Together they form a unique fingerprint.

Cite this