Multimodal Alignment Tasks and Zero-Shot Cross-Lingual Transfer in XLM-R

The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks. However, the lack of labelled task data necessitates a variety of methods aiming to close the gap to high-resource languages. Zero-shot methods in particular, often use translated task data as a training signal to bridge the performance gap between the source and target language(s). We introduce XeroAlign, a simple method for task-specific alignment of cross-lingual pretrained transformers such as XLM-R. XeroAlign uses translated task data to encourage the model to generate sim

Research goal: How does the integration of multimodal alignment tasks (e.g., image-text matching) during intermediate training influence the zero-shot cross-lingual transfer performance of XLM-R on XTREME-R, measured by accuracy improvements on high-resource vs. low-resource languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.2/10.