Shared task at SemEval-2021

Dr. Tristan Miller has co-organized an evaluation campaign at SemEval-2021, the 15th International Workshop on Semantic Evaluation.

The aim of the campain was to provide a unified testing framework for methods for machine learning from data containing multiple and possibly contradictory annotations. Dr. Miller and his colleague, Dr. Edwin Simpson of the University of Bristol, provided a humour classification data set for the campaign. The results will appear in a forthcoming task paper, "SemEval-2021 Task 12: Learning with Disagreements", to be published in the workshop proceedings.

SemEval-2021, colocated with the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL–IJCNLP 2021), will be held on August 5–6, 2021 in Bangkok.