XLM-R Performance in Zero-Shot Cross-Lingual Transfer via Low-Resource Language Tasks

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: What is the impact of using intermediate language-understanding tasks from multiple low-resource languages (e.g., Swahili, Urdu, Hebrew) instead of only high-resource languages on the zero-shot cross-lingual transfer performance of XLM-R on the XTREME-R benchmark, measured by average mF1 scores?

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