# Overview
This challenge concerns natural language processing skills through machine learning techniques. You will work on the story data, where training samples are provided. You will develop suitable classification techniques that will make predictions on unseen test data. The performance will be measured upon submission of the prediction results. A leaderboard will be published after each submission. **You need to use your URN as the Team Name** in the Kaggle page. **Otherwise, your score won't be recorded.** Multiple submissions are encouraged if you wish to improve your models. The latest model for each student will be used for the assessment. You may save multiple prediction results and choose the best one for the final submission.

# Important Rule
You need to use your URN as the Team Name in the Kaggle page. Otherwise, your score won't be recorded.

# Code Submission
You need to submit your code to Surreylearn before the code submission due date (see SurreyLearn for further detail)

# Participation
Please click the join competition button on the page to join it. Otherwise, you cannot submit your result.


# Dataset
### Overview
This is a dataset about **Story**.

In the training set, you will be provided with a story with 5 sentences.

In the testing set, The test task is to predict the right end given from the former 4 story sentences. That is to say, you will be given 4 sentences with 2 option sentences. You need choose which one is correct. Label 0 means you will choose the first option as the correct ending, and 1 means the second one is correct. An example submission will be provided in the Data section.

### Task Example
| 4 Former Story Sentences                                                                                                                                                                        | Right Ending     | Right Ending      |
|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------|-------------------|
| Rick grew up in a troubled household. He never found good support in family, and turned to gangs. It wasn't long before Rick got shot in a robbery. The incident caused him to turn a new leaf. | He is happy now. | He joined a gang. |

### Dataset Size
- Training set: 52665 stories
- Testing set: 1571 stories
### Training and Testing Data
We will provide the full 5 sentences per story for training data, and 4 former story sentences per story for testing data.

# Evaluation
We will evaluate your prediction result on the testing set. So you will need to submit the result on this competition page. **The minimum requirement of this challenge is 60% testing accuracy.**
 
# Submission Format
Your submission should be a csv file, with two columns in it, the first is the id of the test story and the second is its label. We will provide an example of the submission file in the Data Section.