Project for Machine Learning exam Developed by:
- Chiara Luchini
- Marco Mecarelli
- Alessandro Castellani
The description below is taken from Kaggle competition page
CommonLit, Inc., is a nonprofit education technology organization serving over 20 million teachers and students with free digital reading and writing lessons for grades 3-12. Together with Georgia State University, an R1 public research university in Atlanta, they are challenging Kagglers to improve readability rating methods.
In this competition, you’ll build algorithms to rate the complexity of reading passages for grade 3-12 classroom use. To accomplish this, you'll pair your machine learning skills with a dataset that includes readers from a wide variety of age groups and a large collection of texts taken from various domains. Winning models will be sure to incorporate text cohesion and semantics.
In order to use this project, you have to follow passages written in setup and then it's recommended to change runtime in Runtime -> Change runtime modifying None in GPU. The project is divided in different section, one for all the step (libraries import, dataset preprocessing ecc...).
To run this project, you can use Google Colab and upload the file, here is the link. For this project we have used Google Drive to store dataset, so in order to run it properly you have to download dataset from Kaggle competition at this page and then link your own content drive.
We have also used another dataset which is AoA (Age-of-acquisition), this is the website and you download it here.
Project is created with:
- Google Colab or Anaconda (for a local computation)
- Python
- Tensorflow
- Keras
- Sklearn
- XGBoost
This project is licensed under the MIT License - see the LICENSE.md file for details