Performance Diminishment in XLM-R Intermediate-Task Training for Non-English XTREME-R Tasks with Code-Switching and

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 the performance gain from English intermediate-task training on XLM-R diminish when the target non-English tasks in XTREME-R involve code-switching or domain-specific terminology compared to standard news classification?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.