All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass
This addresses efficiency issues in industrial applications like web content classification, offering a scalable solution for multiple tasks.
The paper tackles the problem of high computational cost in multi-task text classification by proposing a method that achieves stronger performance with close to O(1) cost via one forward pass, outperforming baselines on GLUE and a news dataset.
Multi-Task Learning (MTL) models have shown their robustness, effectiveness, and efficiency for transferring learned knowledge across tasks. In real industrial applications such as web content classification, multiple classification tasks are predicted from the same input text such as a web article. However, at the serving time, the existing multitask transformer models such as prompt or adaptor based approaches need to conduct N forward passes for N tasks with O(N) computation cost. To tackle this problem, we propose a scalable method that can achieve stronger performance with close to O(1) computation cost via only one forward pass. To illustrate real application usage, we release a multitask dataset on news topic and style classification. Our experiments show that our proposed method outperforms strong baselines on both the GLUE benchmark and our news dataset. Our code and dataset are publicly available at https://bit.ly/mtop-code.