en-es
en-fr
en-sl
en
0.25
0.5
0.75
1.25
1.5
1.75
2
Actively Learning to Rank Semantic Associations for Personalized Contextual Exploration of Knowledge Graphs
Published on Jul 10, 2017963 Views
Knowledge Graphs (KG) represent a large amount of Semantic Associations (SAs), i.e., chains of relations that may reveal interesting and unknown connections between different types of entities. Applic
Related categories
Chapter list
Actively Learning to Rank Semantic Associations for Personalized Contextual Exploration of Knowledge Graphs00:00
Outline00:14
Untitled00:35
Knowledge Graphs (KGs)00:35
Relational Knowledge in KGs and Semantic Associations01:03
Empowering Comprehension of Web Content01:33
Empowering Comprehension of Web Content - 101:52
Contextual Exploration of KGs02:02
Contextual Exploration of KGs - 102:21
Contextual Exploration of DBpedia with DaCENA02:33
Entity Extraction 03:18
Retrieval of Semantic Associations03:32
Retrieval of Semantic Associations - 103:55
Information Overload in Contextual KG Exploration03:59
Ranking SAs by Estimated Interest: Serendipity 04:26
Ranking SAs by Estimated Interest: Serendipity - 104:35
Ranking SAs by Estimated Interest: Serendipity - 205:20
Example of SAs ranked by Serendipity05:37
Outline06:24
Personalized Exploration of KGs06:31
Active Learning to Rank for SAs07:28
Active Learning to Rank for SAs - 107:43
Active Learning to Rank for SAs - 208:03
Active Learning to Rank for SAs - 308:27
Active Learning to Rank for SAs - 408:43
Active Learning to Rank for SAs - 508:50
Clustering as Bootstrapping09:00
Clustering as Bootstrapping - 109:10
Clustering as Bootstrapping - 209:16
Clustering as Bootstrapping - 309:20
Serendipity as Bootstrapping09:28
Serendipity vs Clustering09:48
Example: Rating of Most Serendipitous SAs (#0)10:27
Example: Rating of Most Serendipitous SAs (#0) - 110:41
Example: Ranking Learned with RankSVM (#0)10:48
Example: Ranking Learned with RankSVM (#0) - 110:51
Example: Rating on Sampled SAs (#1)11:15
Example: Rating on Sampled SAs (#1) - 111:21
Untitled11:27
Example: Ranking Learned with RankSVM (#1)11:28
Example: Ranking Learned with RankSVM (#1) - 111:39
Features for RankSVM11:49
Experiments: Objectives12:30
Experiments: Settings13:01
Experiments: Data13:47
Experiments: Alternative Configurations and Baselines14:31
Results: Personalization Hypothesis15:36
Untitled16:16
Results: Performance (nDCG@10)16:17
Results: Performance (nDCG@10) - 116:40
Results: Performance (nDCG@10) - 216:48
Results: Performance (nDCG@10) - 317:00
Conclusions and Future Work17:22
Questions18:21