Adversarial Multi-task Learning for Text Classification

TL;DR

This paper introduces an adversarial multi-task learning framework for text classification that reduces interference between shared and task-specific features, improving transferability and performance across multiple tasks.

Contribution

The paper proposes a novel adversarial approach to better disentangle shared and private features in multi-task learning for text classification.

Findings

Improved performance on 16 text classification tasks

Shared knowledge transferability to new tasks

Effective disentanglement of shared and task-specific features

Abstract

Neural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing approaches, the extracted shared features are prone to be contaminated by task-specific features or the noise brought by other tasks. In this paper, we propose an adversarial multi-task learning framework, alleviating the shared and private latent feature spaces from interfering with each other. We conduct extensive experiments on 16 different text classification tasks, which demonstrates the benefits of our approach. Besides, we show that the shared knowledge learned by our proposed model can be regarded as off-the-shelf knowledge and easily transferred to new tasks. The datasets of all 16 tasks are publicly available at \url{http://nlp.fudan.edu.cn/data/}