Publications
Dataset · Zenodo · October 26, 2026
KKT segmentation validity: automatic verb-bounded units vs. UD gold clauses (Uzbek)
Ziyoviddin Sirojiddinov, Muftakh Khakimov
Abstract
Data and scripts comparing the automatic verb-bounded units of the KKT analysis pipeline (rule V0) with the gold clauses of the Uzbek Universal Dependencies treebanks UD_Uzbek-UT and UD_Uzbek-UzUDT (1 182 sentences): boundary precision and recall for a broad and a narrow gold definition, and the Heaps-type exponent of the clause-pattern inventory for V0 units, gold clauses on system tags and gold clauses on gold tags.
Natural Language Processing TechniquesSyntax, Semantics, Linguistic VariationSentiment Analysis and Opinion Miningclause segmentationUzbek languageUniversal Dependencies
More by Muftakh Khakimov
- What the Menzerath–Altmann exponent measures: clauses, morphemes and syllables in Uzbek — supplementary packageZenodo · 2026
- Blind pairwise evaluation materials for dictionary-free spelling normalization in a rule-based Uzbek–English MT system (KKT)Zenodo · 2026
- Uzbek MT structure analysis: clause-model hierarchy and measurement-validity diagnostics (code and coded data)Zenodo · 2026
- Uzbek–English MT: Pre-Registered Blind Human Evaluation (corpus, outputs, ratings, scripts)Zenodo · 2026