### Goal

Your goal is to predict whether a given hypothesis is related to its premise by `contradiction`, `entailment`, or whether neither of those is true (`neutral`).
For each sample in the test set, you must predict a 0, 1, or 2 value for the variable.

Those values map to the logical condition as:
> 0 == entailment
1 == neutral
2 == contradiction

### Metric

Your score is the percentage of relationships you correctly predict. This is known as [accuracy](https://en.wikipedia.org/wiki/Accuracy_and_precision#In_binary_classification).

### Submission File Format

You should submit a csv file with exactly 5195 entries **plus** a header row. Your submission will show an error if you have extra columns (beyond `id` and `prediction`) or rows.  

The file should have exactly 2 columns:

*   `id` (sorted in any order)
*   `prediction` (contains your predictions: 0 for entailment, 1 for neutral, 2 for contradiction)

> **id,prediction**  
c6d58c3f69,1
cefcc82292,1
e98005252c,1
58518c10ba,1
c32b0d16df,1
Etc.

You can download an example submission file (`sample_submission.csv`) on the [Data page](https://www.kaggle.com/c/contradictory-my-dear-watson/data).

### Code Submission Requirement

In this code competition, your `submission.csv` file must be generated as an output from a Kaggle notebook. For details on how to submit from a notebook, review the [FAQ on "How do I make a submission?"](https://www.kaggle.com/c/contradictory-my-dear-watson/overview/frequently-asked-questions)