Visiting Lecturer Program (286) – Knowledge Diffusion Network

Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â

Data Engineer at A1 Telekom, Vienna, Austria

Title: Reachability Analysis of Graph Modelled Collections

Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â

Local Organizer:Â Dr. Mahmood Neshati

Time: Sunday, December 24, 2017,Â 13:00

Location:Â Faculty of Engineering and Computer Science, Shahid Beheshti University, Velenjak Street, Tehran, Iran

Abstract:

Nowadays, we have a large number of information sources from different modalities—text, images, audio, video and more. However, information objects are not isolated anymore. They are frequently connected via metadata, semantic links, etc. This leads to various challenges in graph-based Information Retrieval (IR). This talk is concerned with how much such a graph model helps reaching relevant information objects, especially from different modalities. A framework is presented in which different features and relations between information objects are experimented to improve recall. I will present this model, briefly describe some of the experiments, and present its applications in real world challenges