Troubleshooting and Optimizing Named Entity Resolution Systems in the Industry 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

Troubleshooting and Optimizing Named Entity Resolution Systems in the Industry

Published on Jul 15, 20151827 Views

Named Entity Resolution (NER) is an information extraction task that involves detecting mentions of named entities within texts and mapping them to their corresponding entities in a given knowledge

Related categories

Chapter list

Troubleshooting and Optimizing Named Entity Resolution Systems in the Industry00:00
Named Entity Resolution00:23
NER Tools and Frameworks - 101:03
NER Tools and Frameworks - 201:24
NER Tools and Frameworks - 301:42
NER Systems Evaluations01:53
What the evaluations show02:45
Our goal is to avoid the situation below03:07
What we have done for that03:23
How a NER system typically works04:13
When things may go wrong06:05
How do we know what happens in our scenario07:24
Ambiguity Types08:54
Ambiguity Metrics - 110:37
NER Tools and Frameworks - 211:39
Evidence Adequacy Metrics12:38
Interpreting and acting on the metrics - 113:35
Interpreting and acting on the metrics - 215:07
Framework Application Cases16:03
Ambiguity Metrics - 217:00
Evidence Adequacy Metrics - Knowledge Graph Prevalence17:24
From metrics to actions17:43
Wrapping Up18:35
Thank you for your attention!19:21