FORMAL AND NEURAL APPROACHES TO MORPHOLOGICAL ANALYSIS IN AGGLUTINATIVE LANGUAGES: EVIDENCE FROM KAZAKH

Automatic morphological analysis remains a challenging task for agglutinative languages because of their rich inflectional systems, productive derivation, and complex morphophonological rules. Recent neural models, especially transformer-based architectures, have demonstrated impressive empirical performance. However, they frequently exhibit a deficiency in linguistic transparency and encounter challenges in systematic generalization inside low-resource environments. This research offers a comparative and integrative examination of formal (rule-based and finite-state) and neural (KazBERT-based) methodologies for morphological analysis, utilizing the Kazakh language as a case study of low-resource agglutinative morphology. Initially present a formal morphological model that distinctly represents root-affix structure, vowel harmony, and morphotactic restrictions. We next test many neural architectures for morphological disambiguation and tagging, such as KazBERT coupled with CRF-based decoding. In addition to typical accuracy measurements, we do a comprehensive error taxonomy and linguistic analysis, investigating how various model classes manage ambiguity, infrequent forms, and extended affix chains. The findings indicate that whereas neural models excel in surface-level accuracy compared to exclusively rule-based systems, they demonstrate consistent deficiencies in morphologically intricate and infrequent constructs. On the other hand, formal models show better generalization based on language limitations. Based on these results, we suggest a hybrid morphology-aware framework that adds symbolic restrictions to neural inference. This framework consistently improves results in a variety of assessment contexts. The study demonstrates that effective morphological analysis of agglutinative languages requires the integration of neural representation learning with explicit linguistic structure. The results are not tied to any one language and have wider implications for morphology-sensitive NLP in low-resource settings.

1. Marquard C. Neural morphological tagging for Nguni languages. In Proceedings of the Sixth Workshop on African Natural Language Processing (AfricaNLP 2025) / C. Marquard, S. Mawere, F. Meyer // Association for Computational Linguistics. – 2025. – Р. 210-220. https://aclanthology.org/2025.africanlp-1.31.

2. Stenlund M. Surface-level morphological segmentation of low-resource Inuktitut using pre-trained large language models. In Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025) / M. Stenlund, H. Myneni, M. Riedel // University of Tartu Library. – 2025. – Р. 688-696. https://aclanthology.org/2025.nodalida-1.69.

3. Research on morphological knowledge-guided low-resource agglutinative languages-Chinese translation / G. Abudouwaili et al // Complex & Intelligent Systems – 2025. https://doi.org/10.1007/s40747-025-01780-5.

4. Developing a hybrid morphological analyzer for low-resource languages / M. Supriya et al // Applied Sciences. – 2025. – № 15(10). – Р. 5682. https://doi.org/10.3390/app15105682.

5. Baitenova L. Hybrid artificial intelligence architectures for automatic text analysis and computational morphology / L. Baitenova // Frontiers in Artificial Intelligence. – 2025. – № 8. – Р. 1708566. https://doi.org/10.3389/frai.2025.1708566.

6. Yazar B.K. Improving low-resource Kazakh-English and Turkish-English neural machine translation using transfer learning and part-of-speech tags / B.K. Yazar, E. Kiliç, // IEEE Access. – 2025. – № 13. – Р. 32341-32356. https://doi.org/10.1109/ACCESS.2025.3542491.

7. Belth C. Meaning-informed low-resource segmentation of agglutinative morphology. In Proceedings of SCiL 2024. ACL Anthology.

8. Aitim A. Developing methods for automatic processing systems of Kazakh language / A. Aitim // KazATC Bulletin. – 2024. – № 133(4). – Р. 254-265. https://doi.org/10.52167/1609-1817-2024-133-4-254-265.

9. Aitim A. Building a high-quality annotated corpus for Kazakh NLP: a pipeline approach / A. Aitim // Vestnik KazUTB. – 2025. – vol. 4, № 29. https://doi.org/10.58805/kazutb.v.4.29-1092.

10. QNLP – Full Kazakh NLP Suite GitHub repository. Retrieved from https://github.com/Aigerimhub/qnlp.

11. A. Aitim QazNLP: Constraint-Aware Multi-Task Sequence Labeling for Morphologically Rich Low-Resource Languages / A. Aitim // in IEEE Access. – 2026. – vol. 14. – Р. 70955-70974. https://doi.org/10.1109/ACCESS.2026.3691193.

12. Aitim A. LLM-Assisted Weak Supervision for Low-Resource Kazakh Sequence Labeling: Synthetic Annotation and CRF-Refined NER/POS Models / A. Aitim // Applied Sciences. – 2026. – № 16(8). – Р. 3632. https://doi.org/10.3390/app16083632.