NER TEXNOLOGIYASINING MATN TAHLILIDAGI AHAMIYATI
Keywords:
Natural language processing (NLP), deep learning, nested entities, sequence labeling, morphological complexity, information extraction.Abstract
This article explores the theoretical foundations, practical applications, and the necessity of adapting Named Entity Recognition (NER) technology for the uzbek language. It highlights the diverse use cases of NER in areas such as news monitoring, question-answering systems, social media analysis, and domain-specific (medical, legal) text processing, illustrated through relevant examples. The article particularly emphasizes that the morphological complexity and flexible word order of the Uzbek language require specially adapted, deep learning-based approaches in this field.
References
1. Abdurakhmonova, N., Barakhnin, V., Mengliev, D., & Eshkulov, M. (2024). Developing named entity recognition algorithms for Uzbek: Dataset insights and implementation. Data in Brief.
2. Abdurakhmonova, N., Mengliev, D., Barakhnin, V., Eshkulov, M., & Palvanov, B. (2023). Dictionary-based medical text analysis in Uzbek: overcoming the low-resource challenge. Proceedings of the 2023 IEEE Ural-Siberian Conference on Computational Technologies (USCCT).
3. Abrosimov K.I., Mosyagina A.G. Sodner for Russian nested named entity recognition // Computational Linguistics and Intellectual Technologies: Papers from the Annual International Conference "Dialogue". 2002. Issue 21.
4. Andrew Borthwick. 1999. A Maximum Entropy Approach to Named Entity Recognition. PhD thesis, New York University.
5. Grishman, R., and Sundheim, B. 1996. Message understanding conference-6: a brief history. In Proceedings of the 16th Conference on Association for Computational Linguistics, pp. 466–71.
6. Kripke, S. 1982. Naming and Necessity. Boston: Harvard University Press.
7. Turian, J., Ratinov, L., & Bengio, Y. (2010). "Word Representations: A Simple and General Method for Semi-Supervised Learning."
