From Information to Knowledge: an overview of public available Knowledge Graphs

Data dell'evento: 
Venerdì, 27 Luglio, 2018 - 16:00
Room B203, DIAG, via Ariosto 25, Roma
Matteo Cannaviccio
In recent years there has been a proliferation of free and commercial "knowledge graphs" (KGs), which represent real-world entities together with their semantic relationships in a graphical form. Those are becoming a powerful asset both for tech giants, as well as for startups and researchers that are focusing on AI applications (semantic search, data analytics, recommender systems, etc.). The talk will introduce the largest KGs publicly available on the Web such as Wikidata, Freebase, YAGO and DBpedia, providing an overview of the many knowledge-based applications that can be enabled from them.
Matteo Cannaviccio completed his PhD from the Department of Computer Engineering at Roma Tre University in April 2018, under the supervision of prof. Paolo Merialdo. His research interests are in the areas of Information Extraction and Natural Language Processing, and he focused on exploring knowledge extraction techniques from Web texts and tables. He is currently collaborating with Diffbot and DBpedia NLP department to extend knowledge extraction from Wikipedia article texts and his tool, LectorPlus, won the first edition of the DBpedia TextExt Challenge.