Gulu at SemEval-2021 Task 7: Detecting and Rating Humor and Offense

Maoqin Yang
2021 Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)   unpublished
Humor recognition is a challenging task in natural language processing. This document presents my approaches to detect and rate humor and offense from the given English text. This task includes 2 tasks: task 1 which contains 3 subtasks (1a, 1b, and 1c), and task 2. Subtask 1a and 1c can be regarded as classification problems and take ALBERT as the basic model. Subtask 1b and 2 can be viewed as regression issues and take RoBERTa as the basic model. And finally, team-Gulu scores in subtask 1a
more » ... a weighted average F1 score of 0.9190, in subtask 1b with an RMSE score of 0.7405, in subtask 1c with a weighted average F1 score of 0.5561, and in subtask 2 with an RMSE score of 0.5807 on the private leader board.
doi:10.18653/v1/2021.semeval-1.156 fatcat:djez5z2v2jeonjoqqaygm5txhi