Batch Size Effects on Zero-Shot Cross-Lingual Transfer in Multilingual STS Tasks

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 varying the batch size (e.g., 8 vs 32) during intermediate-task fine-tuning affect the zero-shot cross-lingual transfer performance (measured by F1 score) of multilingual models on the XTREME-R benchmark for semantic textual similarity (STS) tasks?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.5/10.