Keywords
How to Cite
Abstract
This paper proposes a search model for an Uzbek electronic terminological dictionary that accounts for spelling variants and affixed forms. Based on research in information retrieval and Uzbek morphological analysis, the framework grounds the stages of spelling normalization, morphological candidate identification, and their verification against the terminological dictionary. The model is designed to preserve the dictionary form of multi-word terms and prioritize exact matches. The work is theoretical and methodological in nature; the software implementation of the model and its experimental evaluation pertain to the next stage.
References
1. Manning C. D., Raghavan P., Schütze H. Introduction to Information Retrieval. Cambridge University Press, 2008. § 2.2.4. https://nlp.stanford.edu/IR-book/
2. Beesley K. R., Karttunen L. Finite State Morphology. Stanford: CSLI Publications, 2003. https://web.stanford.edu/group/cslipublications/cslipublications/site/1575864347.shtml
3. Sharipov M., Salaev U. Uzbek affix finite state machine for stemming. 2022. arXiv preprint. DOI: 10.48550/arXiv.2205.10078.
4. Salaev U. UzMorphAnalyser: A Morphological Analysis Model for the Uzbek Language Using Inflectional Endings. 2024. arXiv preprint, v2. DOI: 10.48550/arXiv.2405.14179.
5. Unicode Consortium. Unicode Standard Annex #15: Unicode Normalization Forms. https://www.unicode.org/reports/tr15/ (murojaat sanasi: 17.10.2026).