Sentiment and Sarcasm Classification with Multitask Learning
Computation and Language
2019-03-12 v2
Abstract
Sentiment classification and sarcasm detection are both important natural language processing (NLP) tasks. Sentiment is always coupled with sarcasm where intensive emotion is expressed. Nevertheless, most literature considers them as two separate tasks. We argue that knowledge in sarcasm detection can also be beneficial to sentiment classification and vice versa. We show that these two tasks are correlated, and present a multi-task learning-based framework using a deep neural network that models this correlation to improve the performance of both tasks in a multi-task learning setting. Our method outperforms the state of the art by 3-4% in the benchmark dataset.
Cite
@article{arxiv.1901.08014,
title = {Sentiment and Sarcasm Classification with Multitask Learning},
author = {Navonil Majumder and Soujanya Poria and Haiyun Peng and Niyati Chhaya and Erik Cambria and Alexander Gelbukh},
journal= {arXiv preprint arXiv:1901.08014},
year = {2019}
}