arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.05752cs.CLcs.AIcs.SI
收藏

并行深度学习驱动的流行文化文本和英语幽默文学中的讽刺检测

Parallel Deep Learning-Driven Sarcasm Detection from Pop Culture Text and English Humor Literature

National Institute of Electronics & Information Technology, Kolkata(印度国家电子与信息技术学院(加尔各答));RCC Institute of Information Technology, Kolkata(RCC信息技术学院(加尔各答))

Sourav Das, Anup Kumar Kolya

摘要:

讽刺是一种复杂的方式包装任何immigrant真理,消息,甚至嘲笑在一个滑稽的方式。使用社交网络的通信的出现大量产生了新的社交途径。可以进一步说,幽默、讽刺、挖苦和机智是现代社会幽默的四辆战车。在本文中,我们手动提取的基准流行文化讽刺语料库,包含讽刺对话和独白讽刺词的分布特征。我们生成输入序列形成的加权向量从这样的话。我们进一步提出了四个并行的深度长短期网络(pLSTM)的合并,每个网络都有不同的激活分类器。这些模块的主要目的是成功地检测讽刺的文本语料库。我们提出的用于检测讽刺的模型在使用讨论的数据集进行训练时,训练准确率为98.95%。对比而言,在所有测试案例中,它在两篇精心挑选的古腾堡计划英语幽默文献上获得了最高的98.31%的总体验证准确率。我们的方法超越了以前的国家的最先进的几个讽刺语料库的作品,并在一个新的黄金标准的性能讽刺检测的结果。

英文摘要:

Sarcasm is a sophisticated way of wrapping any immanent truth, mes-sage, or even mockery within a hilarious manner. The advent of communications using social networks has mass-produced new avenues of socialization. It can be further said that humor, irony, sarcasm, and wit are the four chariots of being socially funny in the modern days. In this paper, we manually extract the sarcastic word distribution features of a benchmark pop culture sarcasm corpus, containing sarcastic dialogues and monologues. We generate input sequences formed of the weighted vectors from such words. We further propose an amalgamation of four parallel deep long-short term networks (pLSTM), each with distinctive activation classifier. These modules are primarily aimed at successfully detecting sarcasm from the text corpus. Our proposed model for detecting sarcasm peaks a training accuracy of 98.95% when trained with the discussed dataset. Consecutively, it obtains the highest of 98.31% overall validation accuracy on two handpicked Project Gutenberg English humor literature among all the test cases. Our approach transcends previous state-of-the-art works on several sarcasm corpora and results in a new gold standard performance for sarcasm detection.

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。

↑