Cross-lingual Transfer Performance in XTREME-R with Intermediate-Task Datasets

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 different intermediate-task datasets (e.g., NLI, QQP, SST) on zero-shot cross-lingual transfer performance for non-English languages in the XTREME-R benchmark, as measured by accuracy and F1 scores?

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