Sentiment and Sarcasm Classification with Multitask Learning

01/23/2019

∙

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.

READ FULL TEXT

Sentiment and Sarcasm Classification with Multitask Learning

Identifying beneficial task relations for multi-task learning in deep neural networks

On the relationship between disentanglement and multi-task learning

Deep Automated Multi-task Learning

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders

Team Neuro at SemEval-2020 Task 8: Multi-Modal Fine Grain Emotion Classification of Memes using Multitask Learning

LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish

Towards automatic construction of multi-network models for heterogeneous multi-task learning

Sentiment and Sarcasm Classification with Multitask Learning

Related Research

Identifying beneficial task relations for multi-task learning in deep neural networks

On the relationship between disentanglement and multi-task learning

Deep Automated Multi-task Learning

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders

Team Neuro at SemEval-2020 Task 8: Multi-Modal Fine Grain Emotion Classification of Memes using Multitask Learning

LTG-Oslo Hierarchical Multi-task Network: The importance of negation for document-level sentiment in Spanish

Towards automatic construction of multi-network models for heterogeneous multi-task learning