Ended 10 months ago
173 participants
1287 submissions

Hidden
Practical Assignment 2: Text multiclass classification: movie's genre

Your task is to classify film descriptions into 6 classes. The metric is Accuracy.

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. To see the score and how many points you get if you can beat him, look at the table below:

baseline Accuracy
LogReg 0.43687
CatBoost 0.23240
LSTM 0.34413
Transformer 0.61340

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 0.75. 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.