CodeT5 Performance in Zero-Shot Cross-Lingual Transfer with Intermediate Task Scaling

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 varying the number of intermediate language-understanding tasks (scaling from 1 to 9 tasks) on the zero-shot cross-lingual transfer performance of CodeT5 in the CodeXGLUE benchmark, evaluated by BLEU score, execution accuracy, and inference latency?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.0/10.