Neural Networks for Information Retrieval

Machine learning plays an important role in many aspects of modern IR systems, and deep learning is applied to all of those. The fast pace of modern-day research into deep learning has given rise to many different approaches to many different IR problems.

  Download slides (PDF, 28MB)

Full-day tutorial at ECIR 2018 on March 26, 2018

Table of contents

The tutorial is organized in 9 parts as described below. For more details, see the overview paper.

Time slot Topic Presenters
09:30 - 10:15 Introduction & preliminaries Tom Kenter section slides 1
section slides 2
10:15 - 11:00 Semantic matching Christophe Van Gysel section slides
11:00 - 11:30 Coffee break
11:30 - 12:15 Learning to rank Bhaskar Mitra section slides
12:15 - 13:00 Entities Tom Kenter, Christophe Van Gysel section slides
13:00 - 14:30 Lunch break
14:30 - 15:15 Modeling user behavior Maarten de Rijke section slides
15:15 - 16:00 Generating Responses Tom Kenter section slides
16:00 - 16:30 Coffee break
16:30 - 17:15 Recommender systems Maarten de Rijke section slides
17:15 - 17:45 Industry insights Tom Kenter, Bhaskar Mitra section slides
17:45 - 18:30 Q + A Tom Kenter, Christophe Van Gysel, Maarten de Rijke, Bhaskar Mitra

ReferencesAll slides


If you wish to refer to the tutorial in your scientific publication, please refer to our overview paper:

  Author = {Kenter, Tom and Borisov, Alexey and Van Gysel, Christophe and Dehghani, Mostafa and de Rijke, Maarten and Mitra, Bhaskar},
  Booktitle = {ECIR 2018},
  Organization = {Springer},
  Title = {Neural Networks for Information Retrieval},
  Year = {2018}}