Scaling Efficiency of Intermediate-Task Training with Task Count on the XTREME Benchmark

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 efficiency of intermediate-task training (measured in training time and computational cost) scale with the number of intermediate tasks when evaluated on the XTREME benchmark?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.1/10.