Research Area:  Machine Learning
Sarcasm detection and sentiment analysis are important tasks in Natural Language Understanding. Sarcasm is a type of expression where the sentiment polarity is flipped by an interfering factor. In this study, we exploited this relationship to enhance both tasks by proposing a multi-task learning approach using a combination of static and contextualised embeddings. Our proposed system achieved the best result in the sarcasm detection subtask.
Author(s) Name:  Abdullah I. Alharbi, Mark Lee
Conferrence name:  Proceedings of the Sixth Arabic Natural Language Processing Workshop
Publisher name:  Association for Computational Linguistics
Paper Link:   https://aclanthology.org/2021.wanlp-1.39/