Intermediate-Task Difficulty Tuning vs. Fine-Tuning for Zero-Shot Transfer in XTREME-R
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: What is the trade-off between inference efficiency and alignment score gains when using intermediate-task difficulty tuning versus standard fine-tuning on English for zero-shot transfer in XTREME-R?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.3/10.
Notes
Files
paper.pdf
Files
(79.0 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:3c3780b9ed5f04970e283512b76f31d9
|
79.0 kB | Preview Download |