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.
Overview of the TREC 2022 NeuCLIR Track
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This is the first year of the TREC Neural CLIR (NeuCLIR) track, which aims to study the impact of neural approaches to cross-language information retrieval. The main task in this year's track was ad hoc ranked retrieval of Chinese, Persian, or Russian newswire documents using queries expressed in English. Topics were developed using standard TREC processes, except that topics developed by an annotator for one language were assessed by a different annotator when evaluating that topic on a different language. There were 172 total runs submitted by twelve teams.
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.