Performance Comparison of M-UNITER on XTREME-M with Intermediate-Task Training Across High-Resource Languages

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 performance of M-UNITER on the XTREME-M benchmark compare when using intermediate-task training on multiple high-resource languages (e.g., English, Spanish, French) versus English alone, measured by zero-shot cross-lingual accuracy?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.