A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning

TL;DR

This paper introduces a flexible multi-task learning architecture with recurrent neural layers that models complex interactions among multiple text classification tasks, leading to significant performance improvements.

Contribution

It proposes a generalized recurrent neural architecture for multi-task learning that captures complex task interactions, surpassing previous simpler models.

Findings

Significant performance improvements on five benchmark datasets.

Effective modeling of complex correlations among three or more tasks.

Flexible architecture adaptable to various multi-task scenarios.

Abstract

Multi-task learning leverages potential correlations among related tasks to extract common features and yield performance gains. However, most previous works only consider simple or weak interactions, thereby failing to model complex correlations among three or more tasks. In this paper, we propose a multi-task learning architecture with four types of recurrent neural layers to fuse information across multiple related tasks. The architecture is structurally flexible and considers various interactions among tasks, which can be regarded as a generalized case of many previous works. Extensive experiments on five benchmark datasets for text classification show that our model can significantly improve performances of related tasks with additional information from others.