Cross-Lingual Transfer Robustness Across High-Resource Language Subsets

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contex

Research goal: How does the robustness of zero-shot cross-lingual transfer (measured by XTREME-M accuracy) vary when intermediate fine-tuning is performed on different subsets of high-resource languages, such as Romance languages versus Germanic languages?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.