Publications
Dataset · Zenodo · November 7, 2026
UzArchMeta-IR: A Metadata-Aware Retrieval Test Collection for Uzbek Digital Archives
Dauletov Adilbek Yusupbayevich, Noila Matyakubova
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.
Information Retrieval and Search BehaviorDigital and Traditional Archives ManagementText and Document Classification Technologiesdocument retrievaltest collectionsUzbek language
More by Noila Matyakubova
- A Multitask XLM-R-Based Hybrid Approach for Named Entity Recognition, Coreference Resolution, and Genealogical Relation Extraction from Uzbek Historical DocumentsMachine Learning and Knowledge Extraction · 2026
- UzAlign v1.1.1: A Morphologically Annotated Uzbek–English Parallel Corpus with Model-Assisted Word AlignmentData · 2026
- UzPoetMeta Gold v1.1: Open Annotations for Metaphor Detection in Classical and Modern Uzbek PoetryZenodo · 2026
- ArchiveGene-RealZenodo · 2026
