Toward AI-assisted identification and disambiguation of literary terminology in Uzbek: Design of an intelligent thesaurus application
Annotatsiya
This paper presents the design of an NLP-based framework for identifying and disambiguating Uzbek literary terms, together with an existing electronic dictionary-thesaurus and its mobile application developed in prior doctoral research. We characterize the terminological polysemy that motivates the work, propose an annotation schema and a graph-structured thesaurus, and describe a framework-classification pipeline and an enhanced mobile interface built on established HCI principles. Empirical training and evaluation of the disambiguation component on source-verified annotations are planned as future work and are not claimed here. The contribution is a design and a resource that address a documented gap in Uzbek digital humanities infrastructure for morphologically complex, low-resource languages.
Hali tarjima qilinmagan