Detecting Errors in Numerical Linked Data using Cross-Checked Outlier Detection thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Detecting Errors in Numerical Linked Data using Cross-Checked Outlier Detection

Published on Dec 19, 20141890 Views

Outlier detection used for identifying wrong values in data is typically applied to single datasets to search them for values of unexpected behavior. In this work, we instead propose an approach whic

Related categories

Chapter list

Detecting Errors in Numerical Linked Data using Cross-Checked Outlier Detection00:00
Numerical Errors in Linked Data00:17
Example: Errors in DBpedia02:01
Our Approach03:09
Challenges03:52
Challenges04:51
Outlier Detection05:46
Detecting Errors using Outlier Detection06:37
Challenge 1 : Masking of Erroneous Values07:11
Challenge 1: Subpopulation Lattice08:11
Challenge 2: Natural Outliers10:28
Experiments11:47
Results13:17
References15:15
Thank you!15:21