Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

This is for archival versions of SemEval task datasets. Instructions:

  • Files: Include all data files: evaluation, train, test data, and if possible, system predictions, evaluation code, evaluation output, as well as a README explaining the contents. Make sure to give the task description paper citation in the README. If there is a webpage specific to the task (e.g. on CodaLab), include that as well.
  • Title: The upload title should be the full task name and year, e.g. "SemEval-2020 Task 1: Name of Task".
  • Authors: Specify the same author list as in the task paper, along with ORCIDs.
  • Description: A short summary of the task and what is in the data release. If there is a webpage specific to the task (e.g. on CodaLab), include that as well.
  • Keywords: Include SemEval-YYYY as a keyword (e.g. SemEval-2020), as well as other relevant terms (e.g. NLP, semantics, corpus; names of languages in your task).
  • Conference: Conference title = "International Workshop on Semantic Evaluation", Acronym = "SemEval", Place = workshop location, Website = SemEval website for that year