BioASQ Prizes

Prizes will be awarded to the winners of both tasks of the challenge.

A total amount of €12,000 will be awarded for the second challenge.

Details about those prizes and the Additional Best Contribution Award by Transinsight are given below.

Please note that the prizes will be awarded to the best teams. If a team participates with 4 different systems, during the calculation of the rankings only the best performance of its systems will be used.

Task 2

Task 2a

Task 2a has three (3) distinct milestones and will be scored against two (2) metrics: the Lowest Common Ancestor F-measure (LCA-F) and the label-based micro F-measure. So there will be a total of six (3x2= 6) rankings. For each one of the rankings, the participating teams ranked on the top two places will be awarded a prize.

Note that a team may take the 1st or 2nd place in more than one ranking, either for the same milestone or a different one. In this case it will be awarded the total of the corresponding prizes.

The total amount which will be awarded for task 2a is €6,000.

Results at: http://bioasq.lip6.fr/results/2a/

Task 2b

Task 2b has two (2) distinct phases. For each of the phases the amount of €3,000 will be awarded (a total of €6,000). Each phase has five (5) distinct milestones. For each one of the milestones, the participating teams ranked on the top two places will be awarded a prize.

Note that, as for Task 2a, a team may take the 1st or 2nd place in both phases. In this case it will be awarded the total of the corresponding prizes.

Results at: http://bioasq.lip6.fr/results/2b/

Transinsight Semantic Intelligence Award 2014

Along with the per-task prizes, an award will be given for the overall best contribution, the Transinsight Semantic Intelligence Award 2014 (offered by  Transinsight).

For a participating system to win this prize, it has to:

  • take part in all tasks and subtasks of the challenges, and
  • obtain the highest overall rank among all participating systems, evaluated as a weighted sum of ranks over all subtasks. Weights are uniformly distributed among all subtasks and among all evaluation metrics within each subtask.

Here is an example:

System Task 2a Task 2b Overall
A 3rd 4th 3+4=7
B 2nd 2nd 2+2=4
C 1st  No participation

Ineligible for the Best Overall
Contribution Award

Winner of the Transinsight Award: System B