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
Srijan Bansal, Vishal Garimella, Ayush Suhane, Jasabanta Patro, Animesh Mukherjee
Computational Social Science and Social Media Short Paper
Session 2A: Jul 6
(08:00-09:00 GMT)
Session 3A: Jul 6
(12:00-13:00 GMT)
Abstract:
In this paper, we demonstrate how code-switching patterns can be utilised to improve various downstream NLP applications. In particular, we encode various 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.
You can open the
pre-recorded video
in a separate window.
NOTE: The SlidesLive video may display a random order of the authors.
The correct author list is shown at the top of this webpage.
Similar Papers
Predicting Performance for Natural Language Processing Tasks
Mengzhou Xia, Antonios Anastasopoulos, Ruochen Xu, Yiming Yang, Graham Neubig,
BENTO: A Visual Platform for Building Clinical NLP Pipelines Based on CodaLab
Yonghao Jin, Fei Li, Hong Yu,
A Systematic Study of Inner-Attention-Based Sentence Representations in Multilingual Neural Machine Translation
Raúl Vázquez, Alessandro Raganato, Mathias Creutz, Jörg Tiedemann,
