A new metric based on subword token alignment predicts cross-lingual transfer in multilingual models better than literal token overlap, especially for different-script language pairs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Literal Token Overlap: Token Alignability for Multilinguality
A new metric based on subword token alignment predicts cross-lingual transfer in multilingual models better than literal token overlap, especially for different-script language pairs.