en-es
en-fr
en-sl
en
0.25
0.5
0.75
1.25
1.5
1.75
2
From hyperlinks to Semantic Web properties using Open Knowledge Extraction
Published on Nov 28, 2017891 Views
Open information extraction approaches are useful but insufficient alone for populating the Web with machine readable information as their results are not directly linkable to, and immediately reusabl
Related categories
Chapter list
From Hyperlinks to Semantic Web Properties using Open Knowledge Extraction00:00
The current Web vs the Semantic Web (Marja-Riitta Koivunen and Eric Miller 2001)00:12
Hyperlinks00:29
Pragmatic trace: presence of a hyperlink in a web page00:52
Linguistic trace: text surrounding a hyperlink01:03
John and Mary went to ISWC 2017, together02:30
However03:18
However - 104:14
Relation extraction04:52
OIE vs OKE05:41
Relevant relations assessment05:58
Relevant Relation Assessment - 106:54
Relevant Relation Assessment - 207:12
Relevant Relation Assessment - 307:16
Relevant Relation Assessment - 407:25
Relevant Relation Assessment - 507:58
Usable predicate generation09:06
Semantic Web triples and properties generation09:17
Semantic Web triples and properties generation - 109:27
Semantic Web triples and properties generation - 210:00
Semantic Web triples and properties generation - 310:11
Semantic Web triples and properties generation - 410:26
Relation formalisation10:37
Semantic Web triples and properties generation10:39
Legalo: Evaluation sample11:04
Hypothesis 1: Relevant relation assessment 11:21
Crowdsourcing tasks for Relevant Relation Assessment11:37
Evaluation results for Relevant Relation Assessment12:04
Hypothesis 2: Usable predicate generation12:11
Crowdsourcing tasks for Usable predicate generation12:30
Evaluation results for Usable Predicate Generation12:41
Crowdsourcing tasks for Usable predicate generation - 112:44
Evaluation results for Usable Predicate Generation - 113:09
Conclusion and next steps13:39
Questions14:40