0.25
0.5
0.75
1.25
1.5
1.75
2
Leveraging and Balancing Heterogeneous Sources of Evidence in Ontology Learning
Published on Oct 21, 20151250 Views
Ontology learning (OL) aims at the (semi-)automatic acquisition of ontologies from sources of evidence, typically domain text. Recently, there has been a trend towards the application of multiple a
Related categories
Chapter list
Leveraging and Balancing Heterogeneous Sources of Evidence in Ontology Learning00:00
Overview – What to expect00:10
Introduction & Concepts01:09
Our Ontology Learning System02:16
Example of an Extended Ontology03:08
System Diagram03:45
Evidence Sources04:55
Data Sources06:00
Heterogeneous Evidence Sources – Part 107:24
Heterogeneous Evidence Sources – Part 207:56
Example of Evidence – Keywords for “CO2”08:18
Concept Selection09:24
Research Questions10:03
Method / Goal11:21
Evaluation setup12:21
Why balancing needed anyway??13:19
Quantity and Quality of Evidence per Source and Seed Concept13:32
Experiments15:51
Accuracy Regarding Number of Evidences Used15:54
Accuracy Regarding Number of Sources17:45
Accuracy Regarding Number of Seed Concepts19:27
Details about Relevance Assessment20:59
Results & Conclusions21:01
Future Work22:15
Thank you23:00