Computational Efficiency Trade-off in Few-shot vs. Zero-shot Cross-lingual Transfer with XLM-R on XTREME-R

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: What is the computational efficiency trade-off between few-shot fine-tuning and zero-shot cross-lingual transfer with intermediate-task training when using XLM-R on XTREME-R, measured in terms of GPU hours per 1% accuracy gain?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.