ADAPTIVE DISTRIBUTED NLP PROCESSING (ADNLP) ALGORITHM FOR LARGE-SCALE UZBEK LANGUAGES TEXTS

Adinaev H. . & Ganijonov S. .


Annotatsiya

This paper proposes an Adaptive Distributed NLP Processing (ADNLP) algorithm for efficient punctuation restoration in large-scale Uzbek text corpora. Traditional BERT-based models require significant computational resources when processing large datasets. The proposed approach integrates Apache Spark–based distributed computing with dynamic partitioning and GPU-aware scheduling mechanisms. Experimental results show that the ADNLP algorithm achieves several times faster performance compared to the conventional sequential processing approach.


Adabiyotlar

  1. Wigan, M. R., & Clarke, R. (2013). Big Data’s Big Unintended Consequences. IEEE Computer Society.
  2. Omar, H. K., & Jumaa, A. K. (2022). Distributed big data analysis using spark parallel data processing. BEEI.
  3. Andersson, L. (2016). Natural Language Processing In A Distributed Environment: A comparative performance analysis of Apache Spark and Hadoop MapReduce. Diva-Portal.
  4. Ikramova, D. T., & Ochilova, M. (2026). Uzbek Agglutinative Morphology vs. English Analytical. Shokh Library.
  5. Salaev, U. (2024). UzMorphAnalyser: A Morphological Analysis Model for the Uzbek Language Using Inflectional Endings. MPASE2024.
  6. Abdurakhmonova, N., et al. (2025). Morpheme segmentation for Uzbek diversity domains. (Reference cited in Salaev & Matlatipov survey).
  7. Walner, A. (2025). Ray vs Dask vs Apache Spark – Comparing DS & ML Engines. Onehouse.
  8. Gagliolo, M., & Schmidhuber, J. (2006). Learning Dynamic Algorithm Portfolios. IDSIA.
  9. Jaggard, A. D., Schapira, M., & Wright, R. N. (2011). Distributed Computing with Adaptive Heuristics.
  10. Zhang, Y. (2024). A survey of dynamic programming algorithms. Applied and Computational Engineering.
  11. Makamo, S. (2024). A Review of Optimization Algorithms in Deep Learning Models. ResearchGate.
  12. Kwon, W., et al. (2023). Efficient Memory Management for LLM Serving with PagedAttention. SOSP.
  13. Hakim, S. A., & Hasan, S. (2025). Explorative Study on Distributed Computing Techniques in LLMs.
  14. Borzunov, A., et al. (2022). Petals: Collaborative inference and fine-tuning of large models.