Knowledge Graph Embedding and its advantages for answering search queries. Simple explanation of Knowledge Graph Embedding and its use case. Tech to answer your (Siri) questions is basically a Deep Graph Knowledge Embedding Library (DGL-KE), a knowledge graph (KG) embeddings library built e.g. on top of Deep Graph Library (DGL). My YouTube video on DGL: https://www.youtube.com/watch?v=d81GrQkvp6I "A knowledge graph is a structured representation of facts, consisting of entities, relationships, and semantic descriptions purposely built for a given domain or application. They are also known as heterogenous graphs, where there are multiple entity types and relation types. " Cited from: https://aws.amazon.com/blogs/machine-learning/training-knowledge-graph-embeddings-at-scale-with-the-deep-graph-library/ DGL is high-performance, scalable Python library for deep learning on multigraphs / graphs. You can now create embeddings for large KGs containing billions of nodes and edges. My vid on Knowledge Graphs: https://www.youtube.com/watch?v=11bAAy8b4sI Links used and presented in my vid (credits to): https://docs.dgl.ai/en/0.7.x/_modules/dgl/data/knowledge_graph.html https://github.com/awslabs/dgl-ke https://dglke.dgl.ai/doc/ https://aws-dglke.readthedocs.io/en/latest/kg.html#training-ke Link to Jupyter Notebook (last section of my video): https://github.com/awslabs/dgl-ke/blob/master/notebook-examples/kge_wikimedia.ipynb #KnowledgeGraph #KnowledgeGraphEmbeddings #QuestionAnsweringTechnology 00:00 DGL API for Knowledge Graphs 02:00 GitHub dgl-ke from awslabs 07:56 Theory of Knowledge Graphs 19:30 Code for Knowledge Graph embedding (example)