Connectionists: Automatic extraction of medications in tweets @ BioCreative VII, track 3 - Call for Participation

[Davy Weissenbacher]

Automatic extraction of medications in tweets @ BioCreative VII - track 3

The goal of this task is to extract the spans of medications in tweets. The
dataset consists of all tweets posted by 212 Twitter users. This data
represents the natural and highly imbalanced distribution of drug mentions
on Twitter, with only approximately 0.2% of the tweets mentioning a
medication. Training and evaluating a sequence labeler on this data set
will closely model the detection of drugs in tweets in practice. See
BioCreative
- Task 3
<https://biocreative.bioinformatics.udel.edu/tasks/biocreative-vii/track-3/>
for more information.

In short:
• 212 Twitter user timelines (~200,000 tweets) annotated with the spans of
medications (timelines have their natural and highly imbalanced
distribution, ~0.2% of the tweets mention a medication)
• Additional balanced dataset of tweets available (4,975+/4,648-)
• Baseline system available
• Codalab opened at https://competitions.codalab.org/competitions/23925
• Evaluation period: Sept. 1st, 9:00 UTC - Sept. 4th, 23:59 UTC

[Apologies for cross-posting]

Best regards,
Davy
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20210608/e87d58fb/attachment.html>