摘要
现有的文本讽刺识别研究通常只关注句子级别的讽刺表达识别,但缺乏考虑讽刺对象对讽刺表达的影响。针对这一问题,该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,该文构建了一个新的面向话题的讽刺识别数据集,包含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,该文提出了一种面向话题的讽刺表达提示学习模型。在该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,该文所提出的面向话题的讽刺表达提示学习模型性能更优。同时,实验分析也表明,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。本文的数据集和代码已发布在https://github.com/HITSZ-HLT/Tosarcasm.
Existing research on sarcasm detection are focused on identifying the sentence-level sarcastic expression,ignoring the influence between satirical objects and sarcastic expressions.This paper proposes a new topic-oriented sarcasm detection task,which helps understand and model the sarcastic expression by introducing the topics as satirical objects.A new dataset for topic-oriented sarcasm detection is constructed,consisting of 707 topics and 4871 topic-comment pairs.Then,a topic-based prompt learning model is proposed to deal with the topic-oriented sarcasm detection task,which is based on the large-scale pre-trained language model and prompt learning.Experimental results on the proposed topic-oriented sarcasm dataset show that the proposed model outperforms the baseline models.Simultaneously,the in-depth analysis shows that the proposed topic-oriented sarcasm detection task is more challenging compared to traditional sentence-level sarcasm detection.The dataset and code are available at https://github.com/HITSZ-HLT/Tosarcasm.
作者
梁斌
林子杰
徐睿峰
秦兵
LIANG Bin;LIN Zijie;XU Ruifeng;QIN Bing(School of Computer Science and Technology,Harbin Institute of Technology,Shenzhen,Guangdong 518055,China;Research Center for Social Computing and Information Retrieval,Harbin Institute ofTechnology,Harbin,Heilongjiang 150006,China;Guangdong Provincial Key Laboratory of Novel Security IntelligenceTechnologies,Shenzhen,Guangdong 518055,China)
出处
《中文信息学报》
CSCD
北大核心
2023年第2期138-147,157,共11页
Journal of Chinese Information Processing
基金
国家自然科学基金(62176076,62006062)
深圳市技术攻关项目(JSGG20210802154400001)
深圳市基础研究学科布局项目(JCYJ20200109113441941)。
关键词
讽刺识别
面向话题的讽刺识别
提示学习
sarcasm detection
topic-oriented sarcasm detection
prompt learning
