MagicPai at SemEval-2021 Task 7: Method for Detecting and Rating Humor Based on Multi-Task Adversarial Training

Jian Ma, Shuyi Xie, Haiqin Yang, Lianxin Jiang, Mengyuan Zhou, Xiaoyi Ruan, Yang Mo


Abstract
This paper describes MagicPai’s system for SemEval 2021 Task 7, HaHackathon: Detecting and Rating Humor and Offense. This task aims to detect whether the text is humorous and how humorous it is. There are four subtasks in the competition. In this paper, we mainly present our solution, a multi-task learning model based on adversarial examples, for task 1a and 1b. More specifically, we first vectorize the cleaned dataset and add the perturbation to obtain more robust embedding representations. We then correct the loss via the confidence level. Finally, we perform interactive joint learning on multiple tasks to capture the relationship between whether the text is humorous and how humorous it is. The final result shows the effectiveness of our system.
Anthology ID:
2021.semeval-1.162
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
1153–1159
Language:
URL:
https://aclanthology.org/2021.semeval-1.162
DOI:
10.18653/v1/2021.semeval-1.162
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.162.pdf