SCRBL

🛠 Contribute: Found a typo? Or any other change in the description that you would like to see? Please consider sending us a pull request in the public repo of the challenge here.

🕵️ Introduction

We absolutely love jigsaw puzzles, feeling a little old for them? Well what if we tell you that the pieces of the puzzle are words and the puzzle has been completely put together. you just answer one simple question , is the puzzle perfect or are some pieces jumbled?

Surely you need vision beyond our eyes to see understand these word-pieces. How do you like them puzzles now 😉!

Welcome to your new challenge. Given a dataset of various texts , predict whether or not they are scrambled/unscrambled.

Understand with code! Here is getting started code for you.😄

💾 Dataset

The dataset consists of around 1 million pieces of texts which has been sourced from the largest encyclopedia in world - Wikipedia!

The dataset is split into train,val and test such that each of the sets has an equal split of the two classes.

📁 Files

Following files are available in the resources section:

• train.zip - (600,002 samples) This contains a csv file which contains 600,002 texts and their corresponding labels.
• val.zip - (100,000 samples) This contains a csv file which contains 100,000 texts and their corresponding labels.
• test.zip - (300,000 samples) This contains a csv file which contains 300,000 texts.

🚀 Submission

• Prepare a CSV containing header as [text,label] and predicted value as scrambled or unscrambled.

Make your first submission here 🚀 !!

🖊 Evaluation Criteria

During evaluation F1 score where,

🔗 Links

• 💪 Challenge Page: https://www.aicrowd.com/challenges/scrbl
• 🗣️ Discussion Forum: https://www.aicrowd.com/challenges/scrbl/discussion
• 🏆 Leaderboard: https://www.aicrowd.com/challenges/scrbl/leaderboards

📱 Contact

• Rohit Midha
• Shraddhaa Mohan
• Sharada Mohanty