F1 Score Efficiency of XLM-R vs. mT5 in Cross-Lingual Transfer with Intermediate Fine-Tuning

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 F1 score gain per 100 GPU hours of XLM-R compare to mT5 when fine-tuning with English intermediate tasks before zero-shot cross-lingual transfer on XTREME-R?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.8/10.