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

2020/05/05 by Srijan Bansal, Vishal Garimella, Bansal, Srijan +7 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Engineering Research #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2005.02295

openalex publication_date 2020/05/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• Global Beats, Local Tongue: Studying Code Switching in K-pop Hits on Billboard Charts

Related

• The Decades Progress on Code-Switching Research in NLP: A Systematic Survey on Trends and Challenges
• How Effective is Incongruity? Implications for Code-mix Sarcasm Detection
• Towards Code-switched Classification Exploiting Constituent Language Resources
• A Survey of Code-switched Speech and Language Processing
• Transfer Learning via Lexical Relatedness: A Sarcasm and Hate Speech Case Study