A knowledge base (KB) is a structured, computer-processable description of the world. A KB can be thought of as a graph, in which the nodes are entities and the edges are relations. Here is an example:
KBs serve all kinds of purposes, such as natural language understanding, intelligent assistance, or machine translation. Our research is guided by specific real-world problems on KBs. I work together with my colleagues and students in the DBWeb team
of Télécom ParisTech
and the Max Planck Institute
. We aim to formalize problems, to design principled models for their solution, and to develop real systems that produce that solution.
Here are the projects that we currently work on:
YAGO is a large knowledge base constructed from WordNet, Wikipedia, and
AMIE is a project to learn patterns and rules in knowledge bases.
Combinatorial creativity: a field of research concerned with making computers creative.
Older projects are
- DIVINA: A system that helps internet users make sure that their internet accounts are safe and secure.
- IBEX: An approach to harvest entities such as people, commercial products, and books from the Web.
- Semantic Culturomics:
This project combines knowledge from newspapers and knowledge bases to mine trends in history and society.
PARIS is a project to learn mappings between knowledge bases.
- LEILA and SOFIE: These are projects that extract ontological information from natural language texts. The projects are no longer actively maintained.
- Watermarking: This project developed methods to protect ontological knowledge against plagiarism.
Students / PostDocs
- Thomas Rebele (PhD student, 2015-)
- Jonathan Lajus (PhD student, 2016-)
- Jérôme Dockès (PhD student, 2016-, co–advised with Gaël Varoquaux)
- Julien Romero (PhD student, 2017-)
- Camille Bourgaux (Postdoc, 2017-)