Publications
Book · Zenodo · October 2, 2026
Trustworthy confidence for Kazakh morphological tagging codebase
Laura M. Baitenova, Akhmed Baikhojayev, Г.С. Мухамеджанова, Gauhar Munaitbas, Сакен Мамбетов, Daryn Nurtaza
Abstract
Code and measured results for the paper "Trustworthy Confidence for Kazakh Morphological Tagging: Calibration and Selective Decision-Making in a Low-Resource Text-Correction Pipeline". One code path measures four taggers — KazBERT, KazRoBERTa, XLM-R base and a feature-based CRF — on the canonical 754/162/162 split of UD_Kazakh-KTB (7,376 / 1,566 / 1,594 tokens, seed 42, decontaminated), with temperature fitted on dev and every calibration/selective-prediction metric evaluated on the held-out test split.
Natural Language Processing TechniquesTopic ModelingSentiment Analysis and Opinion Miningtemperature scalingcalibrationselective prediction
More by Laura Baitenova
- Trustworthy confidence in Kazakh POS tagging: calibration and selective decisions in a low-resource text-correction pipelineFrontiers in Artificial Intelligence · 2026
- Silver-Corpus Transfer for Kazakh Morphosyntactic Analysis: A Cross-Validated Benchmark of Compact and Pretrained ModelsApplied Sciences · 2026
- Context-aware KazRoBERTa with transformer-based candidate re-ranking for Kazakh spelling correctionFrontiers in Artificial Intelligence · 2026
- Character-Aware Gated Fusion CNN–BiLSTM–Transformer with CRFZenodo · 2026
