Gerard de Melo: Large-Scale Data Integration Techniques for Knowledge about Words and Entities

11:00, Room G008 (Parc Club)


An increasing number of applications are making use of explicit knowledge about words and the entities they represent. This talk presents three data integration methods to obtain such knowledge. The first involves learning models to disambiguate word meanings. The second reconciles equivalence and distinctness information about entities from multiple sources. The third method adds a comprehensive taxonomic hierarchy, reflecting how different entities relate to each other. Together, they can be used to produce a large-scale multilingual knowledge base semantically describing over 5 million entities and over 16 million natural language words and names in more than 200 different languages.

Short bio

Gerard de Melo is a post-doctoral researcher at the Max Planck Institute for Informatics in the Databases and Information Systems group led by Gerhard Weikum. Gerard received his doctoral degree from Saarland University. He has published over 15 papers at conferences like CIKM and ACL, and has won two Best Paper awards (ICGL 2008, CIKM 2010). For more information, please visit

Permanent link to this article:

Leave a Reply