Conversational AI

Posted on: Sun, 02/02/2020 - 09:36 By: valentina.janev

Prof. Dr. Jens Lehmann, Lead Scientist for Conversational AI and Knowledge Graphs at Fraunhofer IAIS, presented an overview on current Conversational AI research.


Prof. Lehmann talked about Speech-to-Text, Question Answering via Knowledge Graphs and Text-to-Speech AI systems, and demonstrates the SPEAKER voice assistant platform, which is based on technologies of the Fraunhofer IAIS and IIS institutes. The SPEAKER project was awarded at the AI innovation contest of the BMWi. This lecture was held on last year's FUTURAS IN RES conference with the motto "What's the IQ of AI?". More Info: Fraunhofer IAIS Fraunhofer IIS Conversational AI SPEAKER FUTURAS IN RES

Introduction to Knowledge Graphs

Posted on: Mon, 12/24/2018 - 16:27 By: valentina.janev

This module will introduce the topic of Knowledge Graphs. We will cover what a Knowledge Graph is, the similarities and differences between “world” Knowledge Graphs and Enterprise Knowledge Graphs, as well as theory and practice in the area. In particular, we will discuss the Vadalog Knowledge Graph Management System developed at the University of Oxford.

Extraction for Knowledge Graphs

Posted on: Mon, 12/24/2018 - 16:29 By: valentina.janev

This module will discuss the topic of extraction for Knowledge Graphs. We will focus on web data extraction in this module. Web data extraction is essential to make information available on the web accessible and usable by Knowledge Graphs. We provide a thorough introduction to the topic. This will feature both Oxford’s Vadalog and OXPath systems.

Reasoning in Knowledge Graphs

Posted on: Mon, 12/24/2018 - 16:28 By: valentina.janev

This module will discuss reasoning in Knowledge Graphs. Reasoning is essential to gain value from Knowledge Graphs by deriving insights, and making available new implicit data from existing data. We will cover the theory and practice of reasoning in Knowledge Graphs, and provide a number of easily accessible examples based on Oxford’s Vadalog system.

Introduction to Big Data Architecture

Posted on: Mon, 12/24/2018 - 16:18 By: valentina.janev

This lecture will cover the existing advanced Big Data architectures following a bottom-up approach. In this lecture, the important knowledge to design and architect scalable solutions for challenging problems will be introduced. The primary components in the architecture of such systems and their architectures will be presented and discussed including “inter alia distributed kernels” and cluster managers, distributed file systems and storage systems.

Please, download from the following link.

Big Data Solutions in Practical Use-cases

Posted on: Mon, 12/24/2018 - 16:19 By: valentina.janev

This lecture focuses on architecting Big Data solution. We will discuss the role and importance of the components in realizing system architectures. The participants will be introduced to unique problem characteristics that drive Big Data and the unending technology options to solve them. The application of the introduced concepts and components will be discussed in real-world example of practical use-cases.

Please, downoload from the following links (PPT, Hands-on).

Distributed Big Data Frameworks

Posted on: Mon, 12/24/2018 - 16:20 By: valentina.janev

The “processing frameworks” are one of the most essential components of a Big Data systems. There are three categories of such frameworks namely: Batch-only frameworks (Hadoop), Stream-only frameworks (Storm, Samza), and Hybrid frameworks (Spark, Hive and Flink). In this lecture, we will introduce them and cover one of the major Big Data frameworks, Apache Spark. We will cover Spark fundamentals and the model of “Resilient Distributed Datasets (RDDs)” that are used in Spark to implement in-memory batch computation. Furthermore, essential parts of the important practical techniques will be introduced such as Hadoop Distributed File System for the data resiliency, and  the "lineage" property of “Directed Acyclic Graphs (DAG)” to achieve resilience  for the computation resiliency, or use of catalyst for code optimization. 

Please, downoloadfrom the following link.