Forums

BioCreative'21, Task 3 - Automatic extraction of medication names in tweets Forum

Go back to competition Back to thread list Post in this thread

> Twitter Test Data

Hello,

reading the challenge instructions it is not clear to us whether the test set is (1) from a different set of pregnant women or (2) from the same set of 212 pregnant women in the training set or (3) from totally different people. Could you please give us some more info on this?

Thanks

Posted by: igorkulev @ April 21, 2021, 8:57 a.m.

Dear participants,

The test set is extracted from the set of the 212 "pregnant" women. We kept the same ratio of positive/negative examples.

Best regards,
Davy

Posted by: dweissen @ April 21, 2021, 1:27 p.m.
Post in this thread