EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

QazNLP: Constraint-Aware Multi-Task Sequence Labeling for Morphologically Rich Low-Resource Languages

Aigerim Aitim

IEEE Access · 2026 · 14 · 70955-70974

DOI: 10.1109/access.2026.3691193 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Aigerim Aitim. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Ministry of Culture and Information of the Republic of Kazakhstan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automatic processing of morphologically rich, agglutinative, and low-resource languages remains challenging because productive affixation increases lexical sparsity, weakens statistical generalization, and often produces inconsistent predictions across related linguistic annotation tasks. This study presents QaznLP, a constraint-aware multi-task framework for Kazakh that jointly performs morphological tagging, part-of-speech tagging, and named entity recognition using a shared transformer encoder with task-specific prediction heads. To improve structural reliability, the framework introduces differentiable cross-task compatibility penalties that discourage linguistically invalid label combinations during training and constrained decoding. The study further provides a reproducible evaluation setting based on a cleaned Kazakh news corpus with fixed data splits and robustness diagnostics for out-of-vocabulary tokens, long agglutinative word forms, reduced-data regimes, and cross-task contradiction analysis. In addition, the manuscript explicitly documents the encoder and tokenization setup, justifies the choice of pretrained encoder, reports decoding complexity, and situates the NER component with respect to the KaznERD benchmark. Experimental results show that the proposed model consistently outperforms competitive single-task and shared multi-task baselines in joint average F1, robustness under sparse-data conditions, and structural consistency of predicted labels. The findings indicate that explicit compatibility-aware optimization offers a practical and extensible direction for sequence labeling in morphologically rich low-resource languages.

Förderung

  • the Ministry of Culture and Information of the Republic of Kazakhstan

Zitieren

APA

Aitim, A. (2026). QazNLP: Constraint-Aware Multi-Task Sequence Labeling for Morphologically Rich Low-Resource Languages. IEEE Access, 14, 70955-70974. https://doi.org/10.1109/access.2026.3691193

Vancouver

Aitim A. QazNLP: Constraint-Aware Multi-Task Sequence Labeling for Morphologically Rich Low-Resource Languages. IEEE Access. 2026;14:70955-70974. doi:10.1109/access.2026.3691193

BibTeX
@article{Aitim2026,
  author = {Aitim, Aigerim},
  title = {QazNLP: Constraint-Aware Multi-Task Sequence Labeling for Morphologically Rich Low-Resource Languages},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {70955--70974},
  doi = {10.1109/access.2026.3691193}
}
Kostenlos starten →