Goal
The goal of this InClass competition is to predict the right logical entailment for each sentences couple. Note that the dataset is clearly balanced between all the classes. For every index in the test set, you should predict the correct label, which can only take one of the following three values: contradiction, neutral or entailment.
Metric
Since the dataset is balanced, this competition is evaluated on the categorization accuracy of your predictions (the percentage of logical entailments you get correct).
Submission Format
For each index in the test set, you must predict a label.
The file should contain a header and have the following format:
index,label
0,contradiction
1,neutral
2,entailment
3,contradiction
etc.