Recurrent Neural Network for Text Classification with Multi-Task Learning

TL;DR

This paper introduces a multi-task learning framework using recurrent neural networks to improve text classification by leveraging related tasks, addressing data scarcity issues.

Contribution

It proposes three mechanisms for sharing information in multi-task RNN models, enhancing performance across multiple text classification tasks.

Findings

Improved accuracy on four benchmark datasets

Effective sharing of information between related tasks

Demonstrated benefits of multi-task learning in NLP

Abstract

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we use the multi-task learning framework to jointly learn across multiple related tasks. Based on recurrent neural network, we propose three different mechanisms of sharing information to model text with task-specific and shared layers. The entire network is trained jointly on all these tasks. Experiments on four benchmark text classification tasks show that our proposed models can improve the performance of a task with the help of other related tasks.