Comparative Effectiveness of Zero-Shot Cross-Lingual Transfer on Intermediate English and Non-English Tasks for Low-Resource

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 effectiveness of zero-shot cross-lingual transfer compare between intermediate English tasks (e.g., NLI, QA) and non-English tasks (e.g., Spanish, Arabic) for low-resource languages on XTREME-R?

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