Combining Intermediate-Task Training and Multitask Fine-Tuning for Zero-Shot Cross-Lingual Performance

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-task training on English benchmarks (e.g., GLUE + SuperGLUE) with multitask fine-tuning on XTREME-R further improve zero-shot cross-lingual performance compared to sequential fine-tuning, as measured by accuracy and F1 scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.