0.25
0.5
0.75
1.25
1.5
1.75
2
Semantic Annotation of Data Processing Pipelines in Scientific Publications
Published on Jul 10, 20171031 Views
Data processing pipelines are a core object of interest for data scientist and practitioners operating in a variety of data-related application domains. To effectively capitalise on the experience gai
Related categories
Chapter list
Semantic Annotation of Data Processing Pipelines in Scientific Publications00:00
Unlock Latent Knowledge about DPP00:15
Knowledge about Dataset, Method and Software02:04
Knowledge about Dataset, Method and Software - 103:00
Data Processing Pipeline Knowledge03:05
Data Processing Pipeline Knowledge - 104:15
How? What do we need?04:37
How to describe Knowledge about DPP?05:31
Dataset, Method and Software (DMS) model05:44
How to extract Knowledge about DPP from Scientific Publications?06:52
Scientific Publications07:20
Summary of Approach08:15
Step1 Classify Sentence09:19
Distant Supervision 09:26
Dictionary creation10:24
Training Data Generation12:15
Step2 Extract Named Entities13:04
Named Entity Extraction and Linking13:12
Step3 Create the knowledge repository 14:01
Build a Knowledge Repository14:13
Evaluation14:18
Evaluation - 116:04
How to consume the extracted Knowledge about DPP?16:52
Analyzing Digital Libraries17:11
Application Example18:00
Future work18:47
Untitled19:49