Accueil Accueil

Paris-Saclay Center for Data Science kick-off meeting
The autonomous search engine Maarten de Rijke (5275) - Lundi 30 juin 2014 14:00 - 14:40

The autonomous search engine Maarten de Rijke

Session 2

In the talk I will discuss work on learning to rank for information retrieval, in which the goal is to automatically construct a model that ranks documents in response to a query. In traditional supervised machine learning approaches for the LTR problem one manually selects a set of manually engineered ranking features and then learns the best way of combining them to obtain the most powerful ranking model that those features are capable of producing. In ongoing work on truly autonomous search engines, we are moving evaluation, learning and feature engineering to a weakly supervised paradigm, learning from the implicit feedback that naturally emerges as part of users' interactions with the search engine. I will discuss recent progress in each of these three dimensions: evaluation, learning and feature engineering.

Maarten de Rijke (University of Amsterdam)

Informatique

IN2P3

Il a pour mission de développer et de coordonner les recherches poursuivies dans le domaine de la physique nucléaire, physique des particules et astroparticules.

Toutes les vidéos de l'évenement Paris-Saclay Center for Data Science kick-off meeting (13 videos)

00:16:23.01

2014-06-30

09:30 - 09:50 : Introduction : FCS and Université Paris-Saclay

00:18:17.02

2014-06-30

09:50 - 10:10 : Introduction : Center for Data Science

00:44:35.00

2014-06-30

10:10 - 10:50 : Machine learning for personalized genomics Jean-Philippe Vert

00:26:40.02

2014-06-30

11:20 - 11:45 : Enhancing functional neuroimaging with meta-analytic approaches B...

00:24:48.02

2014-06-30

11:45 - 12:10 : Data science in planetary science Frédéric Schmidt

00:30:18.02

2014-06-30

12:10 - 12:35 : Cosmology: from fundamental questions to computing challenges Rez...

00:32:42.76

2014-06-30

14:00 - 14:40 : The autonomous search engine Maarten de Rijke

00:27:57.78

2014-06-30

14:40 - 15:05 : The digital transition: applications of machine learning to marke...

00:19:33.62

2014-06-30

15:05 - 15:30 : Designing and learning features for music information retrieval J...

00:23:00.03

2014-06-30

15:30 - 15:55 : Direct-touch interaction for scientific visualization Tobias Isen...

00:43:00.01

2014-06-30

16:30 - 17:10 : The data science challenges of particle physics Kyle Cranmer

00:27:18.03

2014-06-30

17:10 - 17:35 : Challenges for data science initiatives – an innovation managem...

01:15:03.01

2014-06-30

17:35 - 18:30 : Panel discussion

Contact Webcast

La cellule webcast du CCIN2P3 vous propose de diffuser en direct et/ou en différé sur internet vos manifestations, colloques, conférences. Attention, ce service est réservé au domaine public dans le domaine de la Recherche Scientifique.


Cellule Webcast
Centre de Calcul IN2P3/CNRS
21 Avenue Pierre de Coubertin
CS70202
69627 VILLEURBANNE Cedex

Tél. :
+33(0) 4.78.93.08.80

Fax. :
+33(0) 4.72.69.41.70



Email :

Voir les mentions légales du site