Impact of Multimodal Intermediate-Task Training on Inference Latency and Throughput in Zero-Shot Cross-Lingual M3C Evaluation
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 impact of multimodal intermediate-task training on inference latency and throughput during zero-shot cross-lingual evaluation on M3C relative to text-only baselines?
Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.
Notes
Files
paper.pdf
Files
(78.2 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:65d3a03c88b297a7bd80d18a9c508db4
|
78.2 kB | Preview Download |