Automatic Construction of a Semantic, Domain-Independent Knowledge Base

Authors:
David Urbansky
Affiliations:
Department of Computer Science, University of Technology Dresden,
Venue:
OTM '09 Proceedings of the Confederated International Workshops and Posters on On the Move to Meaningful Internet Systems: ADI, CAMS, EI2N, ISDE, IWSSA, MONET, OnToContent, ODIS, ORM, OTM Academy, SWWS, SEMELS, Beyond SAWSDL, and COMBEK 2009
Year:
2009

Citing 7
Cited 0

Corroborate and learn facts from the web

Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Language-Independent Set Expansion of Named Entities Using the Web

ICDM '07 Proceedings of the 2007 Seventh IEEE International Conference on Data Mining
The YAGO-NAGA approach to knowledge discovery

ACM SIGMOD Record
Open information extraction from the web

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A probabilistic model of redundancy in information extraction

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Unsupervised named-entity extraction from the Web: An experimental study

Artificial Intelligence
DBpedia: a nucleus for a web of open data

ISWC'07/ASWC'07 Proceedings of the 6th international The semantic web and 2nd Asian conference on Asian semantic web conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we want to show which difficulties arise when automatically constructing a domain-independent knowledge base from the web. We show possible applications for such a knowledge base to emphasize its importance. Current knowledge bases often use manually-built patterns for extraction and quality assurance which does not scale well. Our contribution to the community will be a technique to automatically assess extracted information to ensure high quality of the information and a method of how the knowledge base can be kept up to date. The research builds upon the existing WebKnox system for Web Knowledge Extraction which is able to extract named entities and facts from the web. This is a position paper.