面向话题的讽刺识别:新任务、新数据和新方法(Topic-Oriented Sarcasm Detection: New Task, New Dataset and New Method)

Bin Liang (梁斌), Zijie Lin (林子杰), Bing Qin (秦兵), Ruifeng Xu (徐睿峰)


Abstract
“现有的文本讽刺识别研究通常只停留在句子级别的讽刺表达分类,缺乏考虑讽刺对象对讽刺表达的影响。针对这一问题,本文提出一个新的面向话题的讽刺识别任务。该任务通过话题的引入,以话题作为讽刺对象,有助于更好地理解和建模讽刺表达。对应地,本文构建了一个新的面向话题的讽刺识别数据集。这个数据集包含了707个话题,以及对应的4871个话题-评论对组。在此基础上,基于提示学习和大规模预训练语言模型,提出了一种面向话题的讽刺表达提示学习模型。在本文构建的面向话题讽刺识别数据集上的实验结果表明,相比基线模型,本文所提出的面向话题的讽刺表达提示学习模型取得了更优的性能。同时,实验分析也表明本文提出的面向话题的讽刺识别任务相比传统的句子级讽刺识别任务更具挑战性。”
Anthology ID:
2022.ccl-1.50
Original:
2022.ccl-1.50v1
Version 2:
2022.ccl-1.50v2
Version 3:
2022.ccl-1.50v3
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
557–568
Language:
Chinese
URL:
https://aclanthology.org/2022.ccl-1.50
DOI:
Bibkey:
Cite (ACL):
Bin Liang, Zijie Lin, Bing Qin, and Ruifeng Xu. 2022. 面向话题的讽刺识别:新任务、新数据和新方法(Topic-Oriented Sarcasm Detection: New Task, New Dataset and New Method). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 557–568, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
面向话题的讽刺识别:新任务、新数据和新方法(Topic-Oriented Sarcasm Detection: New Task, New Dataset and New Method) (Liang et al., CCL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ccl-1.50.pdf