A Scalable Approach for Efficiently Generating Structured Dataset Topic Profiles 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

A Scalable Approach for Efficiently Generating Structured Dataset Topic Profiles

Published on Jul 30, 20142121 Views

The increasing adoption of Linked Data principles has led to an abundance of datasets on the Web. However, take-up and reuse is hindered by the lack of descriptive information about the nature of the

Related categories

Chapter list

A Scalable Approach for Efficiently Generating Structured Dataset Topic Profiles00:00
Outline00:24
Introduction01:00
Introduction01:04
Problem and Motivation02:41
Why dataset profiling?02:42
Why dataset profiling?03:37
Approach05:16
Profiling Overview05:21
Dataset profiling Example06:25
Dataset profiling Example06:52
Dataset profiling Example07:24
Resource Instance and Type Extraction07:38
Resource Sampling Approaches08:44
Constructing profiles: Dataset-topic graph10:02
Topic Ranking Approaches11:07
Experimental Setup12:21
Experimental Setup12:33
Baselines13:44
Evaluation Results14:51
Efficiency of Dataset Profiling14:52
Scalability of Dataset Profiling16:13
Motivation Example Revisited!17:46
Conclusion and Future Work18:58
Thank you!20:09