Performance Comparison of Intermediate-Task Training on CodeXGLUE and Natural Language Understanding for Zero-Shot Cross-Lingual

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 performance of intermediate-task training on CodeXGLUE tasks compare to training on natural language understanding tasks for zero-shot cross-lingual code-related tasks (e.g., code generation, code summarization) in models ranging from 100M to 10B parameters, as measured by BLEU score and exact match accuracy?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.