Ended 3 months ago
136 participants
1628 submissions

Hidden
Practical Assignment 2: Text multiclass classification: store's review rating

Your task is to classify the store's review rating into 5 classes. The metric is F1-score.

We present you 4 baseline solutions based on logistic regression, catboost, LSTM and Transformers
You can find them in their respective folders: ./baseline_tfidf_logreg./<catboost_baseline>./baseline_rnn and ./<transformer_baseline> (github repo with baselines). Each of these folders contains a file requirements.txt that will help you with the installation of the dependencies.

You should beat the leaderboard baselines: 

  • The easy baseline has quality 0.65. If you beat it you get 12 points.
  • The hard baseline is 0.68. If you beat this baseline you get 25 point for the task. Good luck!
  • If you will be the first in your group, you'll get 3 bonus points.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.