Semantic Concept Discovery Over Event Databases thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Semantic Concept Discovery Over Event Databases

Published on Jul 10, 2018758 Views

In this paper, we study the problem of identifying certain types of concept (e.g., persons, organizations, topics) for a given analysis question with the goal of assisting a human analyst in writing a

Related categories

Chapter list

Semantic Concept Discovery Over Event Databases00:00
Use Case: Question Analysis00:15
Concept Discovery for Deep Analysis01:49
Event Databases - 105:08
Event Databases - 205:48
Event Databases - 306:38
Our Solution IBM Research ⏤ Semantic Technologies In Use06:58
Question Analysis: Current Prototype - 107:56
Question Analysis: Current Prototype - 208:15
Question Understanding08:24
Question Understanding: Context Details08:44
Concept Search & Ranking: Index-Based Method (co-occurrence) - 108:55
Concept Search & Ranking: Index-Based Method (co-occurrence) - 210:48
IBM Research(context) Analysis Details – Virtual Document Generation11:43
DeepSim (context) Analysis Details – Model Construction & Query Engine12:23
Deep Similarity Analysis (context): Using Semantic Similarity Analysis over GDELT GKG13:28
Swagger API behind DeepSim Analysis14:06
Evaluation: Methodology14:17
Evaluation: Results15:25
Example: Venezuela, Humanitarian Crisis16:33
Conclusion & Future Work17:19