Zero-shot Cross-lingual Performance of mT5-XXL on XTREME-R Subtasks with Intermediate-Task Training
Description
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 zero-shot cross-lingual performance of mT5-XXL on XTREME-R subtasks compare when using intermediate-task training on multiple languages (e.g., Spanish, French) instead of solely English, measured by accuracy gains per subtask?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.
Notes
Files
paper.pdf
Files
(79.1 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:872e4bc838b8ac3a91ce951fff89cd0d
|
79.1 kB | Preview Download |