Interested?

Register for the Workshop Send your Evaluation Problem



When: 1st December 2016
9am – 5pm
Where: BCS, 1st Floor
The Davidson Building
5 Southampton Street
London, WC2E 7HA, UK

A BCS-IRSG Workshop on Practical Issues in Information Access System Evaluation

This workshop intents to bring together on one hand SME's that have (novel) evaluation problems that need to solve, and on the other academic and industrial researchers that have done important work on evaluation - theoretical and practical, with the goal of offering to both groups a hands-on experience on practical issues and solutions to these issues.

The workshop will be of the form of a round table discussion, centered around novel evaluation problems from the practical life in industry and from academic experiences.

Topics for discussion

  • Applications for Evaluation: Search, Summarization, Knowledge, Social Networks, User Analytics, ...
  • Domains for Evaluation: Web, Social, Mobile, Enterprise, Multimedia, ...
  • Evaluation Frameworks: Online evaluation, Log-based evaluation, Collection-based evaluation, Crowdsourcing, User Studies, ...
Confirmed Participants
NameOrganization
Aymeric AgréReportLinker
Karim Cadi ReportLinker
Ingo Frommholz University of Bedfordshire
Charles Hull Flax
Grant Ingersoll Lucidworks
Guillaume Jacquet Joint Research Centre - European Commission
Evangelos Kanoulas University of Amsterdam
Jussi Karlgren KTH and Gavagai
Julia Kiseleva UvA and UserSat
Mounia Lalmas Advertising Sciences, Yahoo!
Jochen Leidner Thomson Reuters
Haiming LiuUniversity of Bedfordshire
Brunella LongoOnline Data Assessment
Artem LukaninRijswijk, Netherlands
Miguel Martinez-Alvarez Signal Media Ltd
Edgar Meij Bloomberg
Peter Mika Schibsted
Jeremy Pickens Catalyst Repository Systems
Vassilis Plachouras Thomson Reuters
Tony Russell-Rose UXLabs
Anne Schuth Blendle
James Shanahan UC Berkeley, Church and Duncan Group
Manos Tsagkias 904Labs
Vasco Visser 904Labs

Are you working for an SME on search algorithms, recommendation algorithms, or components of such systems, e.g. semantics, knowledge graphs, etc? Are you in quest of what are the most recent advances to evaluate the algorithms you built? Do you have any practical issues, or conceived shortcomings for the current evaluation method used? Send us a description of those and participate in the "Evaluation in Practice" Workshop.