Cross-lingual Transfer Efficiency in XTREME-R Fine-tuned Models by Intermediate Task Size

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 impact of varying intermediate task sizes (e.g., small, medium, large) on the efficiency (F1-score per parameter) of zero-shot cross-lingual transfer for models fine-tuned on XTREME-R, particularly for low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.