arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.02295cs.CL
收藏

语码转换模式是提高下游NLP应用性能的有效途径:幽默、讽刺和仇恨语音检测的案例研究

Code-switching patterns can be an effective route to improve performance of downstream NLP applications: A case study of humour, sarcasm and hate speech detection

Indian Institute of Technology, Kharagpur(印度理工学院卡拉格普尔分校)

Srijan Bansal, Vishal Garimella, Ayush Suhane, Jasabanta Patro, Animesh Mukherjee

摘要:

在本文中,我们将展示如何利用代码转换模式来改善各种下游NLP应用程序。特别是,我们编码不同的切换功能,以提高幽默,讽刺和仇恨的语音检测任务。我们相信,这种简单的语言观察也可能有助于改进其他类似的NLP应用程序。

英文摘要:

In this paper we demonstrate how code-switching patterns can be utilised to improve various downstream NLP applications. In particular, we encode different switching features to improve humour, sarcasm and hate speech detection tasks. We believe that this simple linguistic observation can also be potentially helpful in improving other similar NLP applications.

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。

↑