Sentiment and Sarcasm Classification with Multitask Learning

• Abstract
• Abstract (translated by Google)
• URL
• PDF

Abstract

Sentiment classification and sarcasm detection are both important NLP tasks. We show that these two tasks are correlated, and present a multi-task learning-based framework using deep neural network that models this correlation to improve the performance of both tasks in a multi-task learning setting.

Abstract (translated by Google)

URL

http://arxiv.org/abs/1901.08014

PDF

http://arxiv.org/pdf/1901.08014