Personal tools
You are here: Home Events Seminar: Antoine Bordes

Seminar: Antoine Bordes

Modeling Large-Scale Knowledge Bases and Connecting Them to Text

When Nov 15, 2013
from 11:00 AM to 12:00 PM
Where IF-4.31 / IF-4.33
Contact Name
Contact Phone 0131 650 4446
Add event to calendar vCal


Huge amounts of complex data can be represented as multi-relational data, that is, graphs whose nodes stand for concepts and edges for relations among them. In particular, a subset of such data, termed knowledge bases (KBs) became essential tools for storing, manipulating and accessing information in various domains ranging from search (e.g. Google Knowledge Graph) or bioinformatics (e.g. GeneOntology) to recommender systems (e.g. IMDB). However, KB data typically cumulate many difficulties (large numbers of relation types -- some being significantly more represented than others, noisy and incomplete data, or large scale dimensions with up to millions of entities and billions of edges for real-world KBs), that make them hard to be fruitfully inserted into existing frameworks. This talk will present two research directions. First, we will present new approaches for learning representations of  large-scale KB data using energy-based methods, which allow for visualizing and completing them. Then, we will introduce how such representations can be efficiently used to connect KB to text, and hence to improve relation extraction systems. This is a joint work with Google, Université de Montréal, INRIA and Xerox.



Antoine Bordes is a CNRS researcher in the Heudiasyc laboratory of the University of Technology of Compiegne in France. In 2010, he was a postdoctoral fellow in Yoshua Bengio's lab of Université de Montréal. He received his PhD in machine learning from Pierre & Marie Curie University in Paris in early 2010. From 2004 to 2009, he collaborated regularly with the Machine Learning department of NEC Labs of America in Princeton. He received two awards for best PhD from the French Association for Artificial Intelligence and from the French Armament Agency. Antoine's current research concerns large-scale machine learning applied to natural language processing and information extraction, and is funded by the French National Research Agency.

More information about this event…

Document Actions