Performance variation of XLM-R-Base in zero-shot cross-lingual classification with domain-specific intermediate-task training

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 XLM-R-Base on zero-shot cross-lingual classification tasks vary when intermediate-task training is applied to domain-specific datasets (e.g., biomedical or legal) compared to general English intermediate-task training, as measured by F1 score across XTREME benchmark languages?

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