0.25
0.5
0.75
1.25
1.5
1.75
2
Global RDF Vector Space Embeddings
Published on Nov 28, 20171047 Views
Vector space embeddings have been shown to perform well when using RDF data in data mining and machine learning tasks. Existing approaches, such as RDF2Vec, use local information, i.e., they rely on l
Related categories
Chapter list
Global RDF Vector Space Embeddings00:00
Jointly with00:00
Knowledge graphs are all around us.00:09
So, what if Knowledge Graphs could be used for Machine Learning ...00:53
So, what if Knowledge Graphs could be used for Machine Learning ... - 101:13
Challenges01:23
Model Mismatch01:30
Embedding Knowledge Graphs in Vector Spaces02:11
Embedding Goals02:22
How ?03:42
1. Weigh Graph04:13
2. Create Co-occurrence Matrix05:17
2. Create Co-occurrence Matrix (Reversed edges)05:43
2. Create Co-occurrence Matrix (Normalization)07:17
2. Create Co-occurrence Matrix (Normalization) - 107:20
2. Create Co-occurrence Matrix (Optimization)08:11
3. Train a GloVe Model08:38
3. Train a GloVe Model - 109:45
Evaluation Setup10:05
Embedding time10:45
Evaluation Setup : Tasks11:30
Results Summary11:43
Conclusion12:28
Steps Forward13:26
Questions14:33