An Innovative Approach to Semantic Search in Digital Libraries for Low-Resource Languages of Uzbekistan

The 21st century has brought digitization ofknowledge, but as libraries go digital, inclusive search tools arebecoming necessary. Though most digital searches cater to highresourcelanguages, leaving speakers of low-resource languages,like Uzbek, underserved. This research proposes an originalconcept for semantic searches in digital libraries tailoredaround the language, culture, and socio-technical milieu of lowresourcelanguages like Karapalpak, Tajik, and regionaldialects of Uzbek. Our solution integrates numeroussophisticated systems to overcome key challenges like the lackof annotated corpora, embarrassment of morphologicalcomplexity, multilingualism, and others. We design acomprehensive semantic search engine that provides meaningawaresearch results aligned with users' intent, regardless of thelinguistic variations and custom-built domain-specific languageresources, multilingual embeddings, and ontologies used. Theframework enables semi-automatic transliteration, crosslanguageretrieval, context-driven query expansion, and out-oflanguagequery imposition. The system, implemented as aprototype on a Uzbekistan digital library corpus,demonstratively surpasses keyword-based searches in accuracyand user satisfaction. This research will promote thedevelopment of knowledge systems that are more culturallyaligned and relevant to users, applicable to other languages withfew accessible resources.

Hali tarjima qilinmagan