Impact of Intermediate Task Choice and Model Size on Zero-Shot Cross-Lingual Transfer Performance in 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: How does the choice of English intermediate task (e.g., NLI vs. NER) impact zero-shot cross-lingual transfer performance on XTREME-R when using different model sizes (e.g., 110M vs. 770M parameters), evaluated by macro-F1 scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.9/10.