Adversarial Multi-task Learning for Text Classification
This work addresses a specific bottleneck in multi-task learning for text classification, offering incremental improvements in feature separation.
The paper tackles the problem of shared features being contaminated by task-specific features or noise in multi-task learning for text classification, and proposes an adversarial framework that improves performance across 16 different tasks.
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/}