Task Compass: Scaling Multi-task Pre-training with Task Prefix
This addresses the problem of scaling multi-task learning for NLP researchers, though it appears incremental as it builds on existing pre-training trends.
The paper tackles the challenge of negative interference in multi-task pre-training by proposing a task prefix guided framework to explore task relationships, achieving human-parity results on commonsense reasoning leaderboards.
Leveraging task-aware annotated data as supervised signals to assist with self-supervised learning on large-scale unlabeled data has become a new trend in pre-training language models. Existing studies show that multi-task learning with large-scale supervised tasks suffers from negative effects across tasks. To tackle the challenge, we propose a task prefix guided multi-task pre-training framework to explore the relationships among tasks. We conduct extensive experiments on 40 datasets, which show that our model can not only serve as the strong foundation backbone for a wide range of tasks but also be feasible as a probing tool for analyzing task relationships. The task relationships reflected by the prefixes align transfer learning performance between tasks. They also suggest directions for data augmentation with complementary tasks, which help our model achieve human-parity results on commonsense reasoning leaderboards. Code is available at https://github.com/cooelf/CompassMTL