Zero-shot Cross-lingual Transfer vs. Few-shot Fine-tuning in TyDi QA Evaluation

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 zero-shot cross-lingual transfer performance of English intermediate-task trained models compare to few-shot fine-tuned multilingual models on the TyDi QA benchmark when evaluated using F1 score?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.