All Birds with One Stone: Multi-task Text Classification for Efficient Inference with One Forward Pass

TL;DR

This paper introduces a scalable multi-task text classification method that achieves near O(1) inference cost with a single forward pass, improving efficiency in industrial applications like web content classification.

Contribution

The paper proposes a novel multi-task learning approach that reduces inference complexity from N to approximately one forward pass, enabling efficient multi-task classification.

Findings

Outperforms strong baselines on GLUE benchmark

Achieves near O(1) inference cost

Demonstrates effectiveness on news classification dataset

Abstract

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.