Cross-lingual Transfer Performance in Multi-task vs. Single-task Training for XTREME

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 combining multiple intermediate tasks (e.g., ensemble of NLI, QA, and STS) versus single-task training on zero-shot cross-lingual transfer for XTREME tasks, evaluated using XTREME-R scores?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.1/10.