Cross-Domain Intermediate Task Combination for Enhanced Zero-Shot Cross-Lingual Transfer in XTREME-R

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: Does combining intermediate tasks across multiple domains (e.g., natural language understanding + code generation) improve zero-shot cross-lingual transfer performance on XTREME-R compared to single-domain intermediate tasks, as measured by accuracy and F1-score?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.