Deep Multi-Task Learning with Shared Memory
This work addresses data scarcity in neural networks for researchers in multi-task learning, but it is incremental as it builds on existing multi-task and memory-augmented approaches.
The paper tackles the problem of insufficient training data in single-task neural models by proposing deep multi-task learning architectures with a shared external memory, which improved performance on text classification tasks.
Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training data. In this paper, we propose two deep architectures which can be trained jointly on multiple related tasks. More specifically, we augment neural model with an external memory, which is shared by several tasks. Experiments on two groups of text classification tasks show that our proposed architectures can improve the performance of a task with the help of other related tasks.