KLEJ Benchmark

The KLEJ benchmark (Kompleksowa Lista Ewaluacji Językowych) is a set of nine evaluation tasks for the Polish language understanding.

Key benchmark features:

  • It contains a diverse set of tasks from different domains and with different objectives.
  • Most tasks are created from existing datasets but we also release the new sentiment analysis dataset from an e-commerce domain.
  • It includes tasks which have relatively small datasets and require extensive external knowledge to solve them. It promotes the usage of transfer learning instead of training separate models from scratch.

Additionally, we provide automatic evaluation and release an online leaderboard to enable sharing your model results. The benchmark is model-agnostic, the only requirement is to prepare a submission file in a specified format.

KLEJ benchmark was created at Allegro and you can contact us at: klejbenchmark@allegro.pl