Welcome to PolEval 2019!

PolEval is a SemEval-inspired evaluation campaign for natural language processing tools for Polish. Submitted tools compete against one another within certain tasks selected by organizers, using available data and are evaluated according to pre-established procedures.

In 2019 we have announced the following tasks:

  1. Recognition and normalization of temporal expressions
  2. Lemmatization of proper names and multi-word phrases
  3. Entity linking
  4. Machine translation
  5. Automatic speech recognition
  6. Automatic cyberbullying detection

PolEval 2019-related papers will be presented at AI & NLP Workshop Day in Warsaw, Poland (May 31, 2019) and workshop proceedings will be published by the Institute of Computer Science, Polish Academy of Sciences.

Discussion forum

Please join the discussion forum, where you can ask questions about the tasks.

Plans for 2020

The following tasks are planned for the next year's edition of PolEval:

  1. Fake news detection
  2. Submit your own task proposal!