Performance Generalization of English Intermediate-Task Training on Cross-Lingual Benchmarks

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 improvement from English intermediate-task training on XTREME-R generalize to other cross-lingual benchmarks like XTREME-R+, as measured by average accuracy and per-language variance?

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