CodeT5 Intermediate-Task Training for Zero-Shot Cross-Lingual Code Generation

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 effect of intermediate-task training on zero-shot cross-lingual transfer for code generation tasks (e.g., CodeXGLUE) when using multilingual models like CodeT5, and how does it compare to monolingual baselines in terms of BLEU score?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.6/10.