Zero-Shot Cross-Lingual Transfer Performance of XLM-R Across Intermediate Task Types and Language Families

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 task type (e.g., NLI, NER, QA) influence the zero-shot cross-lingual transfer performance of pre-trained multilingual models like XLM-R when measured by accuracy on XTREME-R tasks across different language families?

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