How does the size of the intermediate-task training dataset scale with the zero-shot cross-lingual performance gains of

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 size of the intermediate-task training dataset scale with the zero-shot cross-lingual performance gains of multilingual models on XTREME tasks, and what is the minimal dataset size required to achieve significant improvements in F1 score?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.