Fine-tuning multilingual retrieval models on an even mix of native and Latin-transliterated training queries largely closes the retrieval gap caused by transliterated queries, with full closure only when scripts overlap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Lost in Transliteration: Bridging the Script Gap in Neural IR
Fine-tuning multilingual retrieval models on an even mix of native and Latin-transliterated training queries largely closes the retrieval gap caused by transliterated queries, with full closure only when scripts overlap.