Evaluation plan
The classification systems’ performance will be measured in terms of macro-averaged precision, macro-averaged recall, and macro-averaged F-Score across all the classes. Participants are encouraged to check their system with Sklearn classification report
https://scikit-learn.org/stable/modules/generated/sklearn.metrics.classification_report.html
The participants are required to submit the predicted data in a tab-separated single file named 'predictions.csv’.
Submission should be a .zip file with your team name containing .csv files for individual languages :
Format: Team_name.zip ---> Team_name_languages.csv
e.g. VEL.zip ---> VEL_Tamil.csv, VEL_Malayalam.csv
If you have 3 run submissions, mention the runs in the csv file name
e.g. VEL.zip ---> VEL_Tamil_run1.csv, VEL_Tamil_run2.csv, VEL_Malayalam_run1.csv, VEL_Malayalam_run1.csv
For more information, please check the codalab link:
https://codalab.lisn.upsaclay.fr/competitions/19310#learn_the_details-evaluation