arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.10336cs.AIcs.CL
收藏

SemEval-2021上的MagicPai任务7:基于多任务对抗训练的幽默检测和评级方法

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

Ping An Life Insurance, Ltd.(平安人寿保险股份有限公司)

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

摘要:

本文描述了MagicPai的SemEval 2021任务7的系统,HaHackcraft:检测和评级幽默和冒犯。该任务旨在检测文本是否幽默以及幽默程度。比赛有四个子任务。在本文中,我们主要提出了我们的解决方案,一个基于对抗性示例的多任务学习模型,用于任务1a和1b。更具体地说,我们首先对清理后的数据集进行矢量化,并添加扰动以获得更鲁棒的嵌入表示。然后,我们通过置信水平校正损失。最后,我们对多个任务进行交互式联合学习,以捕捉文本是否幽默和幽默程度之间的关系。最后的结果表明了该系统的有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑