Automatically Generating Data Linkages Using a Domain-Independent Candidate Selection Approach thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Automatically Generating Data Linkages Using a Domain-Independent Candidate Selection Approach

Published on Nov 25, 20112628 Views

One challenge for Linked Data is scalably establishing high quality owl:sameAs links between instances (e.g., people, geographical locations, publications, etc.) in different data sources. Traditional

Related categories

Chapter list

Automatically Generating Data Linkages Using A Domain-Independent Candidate Selection Approach00:00
Outline00:18
Introduction00:39
The General/Naive Approach01:53
Related Work05:13
System Framework - 105:34
Learning Blocking Properties from RDF Graphs06:41
Combining Properties09:24
System Framework - 211:20
Indexing Instances11:30
Selecting Candidate Instance Pairs13:20
Alternative Similarity Measures14:29
Evaluation15:49
Datasets16:45
Learned Candidate Selection Key16:54
Evaluation on RDF Datasets17:14
Evaluation on Non-RDF Datasets18:07
Scalability of Candidate Selection18:56
Runtime of Candidate Selection19:08
Runtime Speedup of the Entire Entity Coreference Process19:26
Conclusion and Future Work20:11