Zero-Shot Cross-Lingual Transfer Accuracy in XTREME-R: Comparing Intermediate Task Selection and Pretraining Strategies for

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 choice of intermediate English task (e.g., NLI, QA, or sentiment analysis) affect zero-shot cross-lingual transfer accuracy on XTREME-R for specific low-resource language families when using multilingual versus monolingual (English-only) pretrained transformers?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.