A Generalized Recurrent Neural Architecture for Text Classification with Multi-Task Learning
This addresses a limitation in multi-task learning for text classification, though it appears incremental as it builds on existing recurrent neural network approaches.
The paper tackles the problem of modeling complex correlations among three or more tasks in multi-task learning for text classification, proposing a flexible architecture with four recurrent neural layers that significantly improves performance on five benchmark datasets.
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.