Scaling Computational Efficiency of Multi-Task Intermediate Training with Task Number and Cross-Lingual Performance

Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tas

Research goal: How does the computational efficiency (training time, memory usage) of multi-task intermediate training scale with the number of tasks, and does it justify the gains in cross-lingual zero-shot performance on the XTREME benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.