Sarcasm detection is important for several NLP tasks such as sentiment identification in product reviews, user feedback, and online forums. It is a challenging task requiring a deep understanding of language, context, and world knowledge. In this paper, we investigate whether incorporating commonsense knowledge helps in sarcasm detection. For this, we incorporate commonsense knowledge into the prediction process using a graph convolution network with pre-trained language model embeddings as input. Our experiments with three sarcasm detection datasets indicate that the approach does not outperform the baseline model. We perform an exhaustive set of experiments to analyze where commonsense support adds value and where it hurts classification. Our implementation is publicly available at: https://github.com/brcsomnath/commonsense-sarcasm.

翻译：在产品审查、用户反馈和在线论坛中查明情绪、用户反馈和在线论坛等若干国家劳工政策任务中,讽刺性探测很重要,这是一项艰巨的任务,需要深入了解语言、背景和世界知识。在本文中,我们调查将常识知识纳入常识知识是否有助于讽刺性探测。为此,我们利用一个有预先培训的语言模型嵌入的图象变迁网络,将常识知识纳入预测过程。我们用三个讽刺性探测数据集进行的实验表明,该方法并不优于基线模型。我们进行了一系列详尽的实验,分析常识支持在哪些方面增加了价值,哪些地方会损害分类。我们的实施情况在https://github.com/brcsomnath/commonsense-sarcasm上公布。