Browse wiki

Jump to: navigation, search
Automatically refining the Wikipedia infobox ontology
Abstract The combined efforts of human volunteers hThe combined efforts of human volunteers have recently extracted numerous facts from Wikipedia, storing them as machine-harvestable object-attribute-value triples in Wikipedia infoboxes. Machine learning systems, such as Kylin, use these infoboxes as training data, accurately extracting even more semantic knowledge from natural language text. But in order to realize the full power of this information, it must be situated in a cleanly-structured ontology. This paper introduces KOG, an autonomous system for refining Wikipedia's infobox-class ontology towards this end. We cast the problem of ontology refinement as a machine learning problem and solve it using both SVMs and a more powerful joint-inference approach expressed in Markov Logic Networks. We present experiments demonstrating the superiority of the joint-inference approach and evaluating other aspects of our system. Using these techniques, we build a rich ontology, integrating Wikipedia's infobox-class schemata with WordNet. We demonstrate how the resulting ontology may be used to enhance Wikipedia with improved query processing and other features.roved query processing and other features.
Added by wikilit team Added on initial load  +
Collected data time dimension Longitudinal  +
Comments The autonomous system proposed in this paper, KOG, makes a step towards refining Wikipedia's ontology which eventually enhance question answering systems and allow them to answer SQL-like queries.
Conclusion Our experiments show that joint-inference Our experiments show that joint-inference dominates other methods, achieving an impressive 96.8% precision at 92.1% recall. The resulting ontology contains subsumption relations and schema mappings between Wikipedia’s infobox classes; additionally, it maps these classes to WordNet.ionally, it maps these classes to WordNet.
Conference location Beijing, China +
Data source Experiment responses  + , Websites  + , Wikipedia pages  +
Dates 21-25 +
Doi 10.1145/1367497.1367583 +
Google scholar url  +
Has author Fei Wu + , Daniel S. Weld +
Has domain Computer science +
Has topic Ontology building +
Month April  +
Pages 635-644  +
Peer reviewed Yes  +
Publication type Conference paper  +
Published in Proceeding of the 17th international conference on World Wide Web +
Publisher Association for Computing Machinery +
Research design Experiment  + , Statistical analysis  +
Research questions This paper presents the Kylin Ontology GenThis paper presents the Kylin Ontology Generator (KOG), an autonomous system that builds a rich ontology by combining Wikipedia infoboxes with WordNet using statistical-relational learning. Each infobox template is treated as a class, and the slots of the template are considered as attributes/slots. Applying a Markov Logic Networks (MLNs) model [28], KOG uses joint inference to predict subsumption relationships between infobox classes while simultaneously mapping the classes to WordNet nodes. KOG also maps attributes between related classes, allowing property inheritance.ed classes, allowing property inheritance.
Revid 10,674  +
Theories Undetermined
Theory type Design and action  +
Title Automatically refining the Wikipedia infobox ontology
Unit of analysis Article  +
Url  +
Wikipedia coverage Main topic  +
Wikipedia data extraction Dump  +
Wikipedia language English  +
Wikipedia page type Article  +
Year 2008  +
Creation dateThis property is a special property in this wiki. 15 March 2012 20:24:08  +
Categories Ontology building  + , Computer science  + , Publications  +
Modification dateThis property is a special property in this wiki. 30 January 2014 20:20:47  +
hide properties that link here 
  No properties link to this page.


Enter the name of the page to start browsing from.