Recurrent Neural Network for Text Classification with Multi-Task Learning
This work addresses data scarcity in natural language processing for researchers and practitioners, but it is incremental as it builds on existing multi-task learning frameworks.
The paper tackled the problem of insufficient training data in neural network models for text classification by using multi-task learning to jointly learn across multiple related tasks, resulting in improved performance on four benchmark tasks.
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.