Work

UzArchMeta-IR: A Metadata-Aware Retrieval Test Collection for Uzbek Digital Archives

Year: 2026
Type: dataset
Abstract: UzArchMeta-IR is a test collection for document retrieval in Uzbek digital archives (Cyrillic and Latin script). It contains 232 documents (title, date, full text), 120 queries and 2,504 graded relevance judgments on a 0–3 scale. 639 pairs are relevant (grade ≥ 2). An official query-level split is provided: train 72, validation 24, test 24 queries. Judgments are given in CSV and TREC formats, with audit files and checksums.
Language: Uzbek
Open Access status: green
OpenAlex ID: W7225462071
Cites:
Cited by:
Related to: 10