Several clarifications for the first round of the Data Clustering Contest
Some articles in the first evaluation data set
were missing the attribute article:published_time due to an issue on our side. The problem has now been fixed.
If this issue was causing your app to crash, kindly notify us in the @contests
group so that we can relaunch your algorithm on the updated data set (don't forget to mention your spiritual animal).2.
For your information, we will always use the following launch order for testing all submissions:
tgnews languages raw_source_dir
tgnews news en_source_dir
tgnews news ru_source_dir
tgnews categories en_source_dir
tgnews categories ru_source_dir
tgnews threads en_source_dir
tgnews threads ru_source_dir
tgnews top en_source_dir
tgnews top ru_source_dir3.
If your submission is not working but can be fixed without changing the source code
or resubmitting the binary (e.g. by installing dependencies, changing launch parameters) you can write detailed instructions in a comment on contest.com and then ping us in @contests
. If we have to fix your submission, we will apply relevant penalties during final scoring.
Unfortunately, if your submission requires a change in the source code
or resubmitting the binary
to start working, we will not be able to help you at this stage.
Stay tuned for the second evaluation data set coming soon.