Rule Mining in Knowledge Bases

Date(s) - 19/05/2016
10:00 am - 11:00 am



The continuous progress of Information Extraction (IE) techniques has led to the construction of large Knowledge Bases (KBs)  containing facts about millions of entities such as people, organizations and places. KBs are important nowadays because they  allow computers to understand the real world and are used in multiple domains and applications. Furthermore, the discovery of useful and non-trivial patterns in KBs, known as rule mining, opens the door for multiple applications in the areas of data analysis, link prediction and  automatic data engineering. In this talk I introduce AMIE, a system that learns logical rules on RDF KBs operating under the Open World Assumption. The scale of current KBs as well as their inherent incompleteness and noise make this endeavor challenging. In addition I show how rule mining can be applied to multiple data analysis and maintenance tasks.


Speaker: Luis Galárraga

Luis Galárraga is a doctoral student in the DBWeb Group of the INFRES department at Télécom ParisTech. He completed his bachelor studies in Computer Engineering at Escuela Superior Politécnica del Litoral (Guayaquil, Ecuador) in 2008 and pursued a Master in Computer Science at Saarland  University in 2009. For his master thesis he worked in the area of Distributed RDF Query Processing under the supervision of Katja Hose and Ralf Schenkel. In 2012 he was granted an IMPRS scholarship to pursue his PhD studies and joined the Ontologies Group, led by Fabian Suchanek, at the Max Planck Institute for Informatics in Saarbrücken to work in the area of Rule Mining on Ontological Knowledge Bases, under
Fabian’s supervision. His work in this topic led to the development and publication of  a system called AMIE (Association Rule Mining Under Incomplete Evidence) for rule mining on RDF Knowledge Bases. In 2013, he did an internship at Google Mountain where he worked in the detection of new entities from web extractions. In 2014 the Ontologies group moved to Télécom ParisTech. Since then, his work has been focused on the application of rule mining in different data maintenance tasks such as Ontology Schema Alignment, Prediction of Semantic Links between entities in Wikipedia and his ongoing work in Predicting Completeness in Knowledge Bases.