Consistency of English Intermediate-Task Training Improvements on XTREME Across Low- and High-Resource Languages in Zero-Shot

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: Is the improvement from English intermediate-task training on XTREME consistent across low-resource target languages compared to high-resource languages in zero-shot settings?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.