Impact of Domain Alignment on Zero-Shot Cross-Lingual Transfer Accuracy

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 domain alignment between the English intermediate task (e.g., biomedical vs. general) and the target XTREME task (e.g., TyDi QA vs. XCOPA) impact zero-shot cross-lingual transfer accuracy when varying the intermediate training corpus size?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.