Artificial Intelligence (AI) is the pinnacle of digitalization; AI is revolutionizing how we work and live. We now have more data than ever about our business processes, and Deep Learning, in particular, gives us the tools to create real value from our data. With AI, we can improve our processes' efficiency; we can improve quality or do completely new things by creating new business models. With AI, computers can understand audio and text in natural language, allowing them to create new user experiences.
This is a Lecture delivered at the Big Data Analytics Summer School 2020 by Dr. Simon Scerri, Fraunhofer IAIS.
The increasing availability of scholarly metadata in the form of Knowledge Graphs (KG) offers opportunities for studying the structure of scholarly communication and the evolution of science. Such KGs build the foundation for knowledge-driven tasks e.g., link discovery, prediction and entity classification which allows to provide recommendation services. Knowledge graph embedding (KGE) models have been investigated for such knowledge-driven tasks in different application domains.
The size and number of knowledge graphs have increased tremendously in recent years. In the meantime, the distributed data processing technologies have also advanced to deal with big data and large scale knowledge graphs. This lecture introduces Scalable Semantic Analytics Stack (SANSA), which addresses the challenge of dealing with large scale RDF data and provides a uni ed framework for applications like link prediction, knowledge base completion, querying, and reasoning.
Mikhail Galkin (Fraunhofer IAIS) Lecture
In the Big Data era, where variety is the most dominant dimension, the RDF data model enables the creation and integration of actionable knowledge from heterogeneous data sources. However, the RDF data model allows for describing entities under various contexts, e.g., people can be described from its demographic context, but as well from their professional contexts. Context-aware description poses challenges during entity matching of RDF datasets the match might not be valid in every context.
Prof. Dr. Jens Lehmann, Lead Scientist for Conversational AI and Knowledge Graphs at Fraunhofer IAIS, presented an overview on current Conversational AI research.
This module will cover the setup, APIs and different layers of SANSA. At the end of this module, the audience will be able to execute examples and create programs that use SANSA APIs. The final part of this lecture is planned to be an interactive session to wrap up the introduced concepts and present attendees some open research questions which are nowadays studied by the community.
This module will cover the needs and challenges of distributed analytics and then dive into the details of scalable semantic analytics stack (SANSA) used to perform scalable analytics for knowledge graphs. It will cover different SANSA layers and the underlying principles to achieve scalability for knowledge graph processing.
Please, download from the following link.