Mukhriddin Eshkulov

Dr. Mukhriddin Eshkulov

Physics, Jizzakh Polytechnic Institute, Jizzakh, Uzbekistan
orcid
The true sign of intelligence is not knowledge but imaginati...

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 April 2024 in Data in Brief
Verified
Journal Article
Open access
Davlatyor MenglievDavlatyor Mengliev
Davlatyor Mengliev
Vladimir BarakhninVladimir Barakhnin
Vladimir Barakhnin
Nilufar AbdurakhmonovaNilufar Abdurakhmonova
Nilufar Abdurakhmonova
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
This paper presents a dataset and approaches to named entity recognition (NLP) in Uzbek language, in a resource-constrained language environment. Despite the increase in NLP applications, the Uzbek language is still underrepresented, which underscores the importance of our work. Our dataset includes 1,160 sentences with nearly 19,000 word forms annotated for parts of speech and named entities, making it a valuable resource for linguistic research and machine learning applications in Uzbek. In addition, for practical application and experiments, the authors have developed two algorithms that, using this dictionary, identifies named entities in Uzbek language texts. In addition, the authors described the methodology for creating the dataset, the design of the algorithms, and their application to the Uzbek language. This study not only provides an important dataset for future named entity recognition(NER) tasks in the Uzbek language, but also offers a methodological basis for the use of vocabulary-based NER or Machine learning NER in other low-resource languages (e.g. Karakalpak). The dataset (and algorithms) we have developed can be used to create applications such as improved chatbot systems, text mining applications and other analytical tools for the Uzbek language, contributing to the development of those areas in the region for which these solutions will be developed.

20 December 2024 in Data in Brief
Verified
Journal Article
Open access
Davlatyor MenglievDavlatyor Mengliev
Davlatyor Mengliev
Vladimir BarakhninVladimir Barakhnin
Vladimir Barakhnin
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
BIBahodir Ibragimov
Bahodir Ibragimov
SMShohrux Madirimov
Shohrux Madirimov
In this study, the authors presented a dataset for named entity recognition in the Uzbek language. The dataset consists of 2000 sentences and 25,865 words, and the sources were legal documents and hand-crafted sentences annotated using the BIOES scheme. The study is complemented by the fact that the authors demonstrated the applications of the created dataset by training a language model using the CNN + LSTM architecture, which achieves high accuracy in NER tasks, with an F1 score of 90.8 %, precision of 93.9 %, and recall of 88.0 % on the test set. The proposed dataset and trained model contribute to the development of natural language processing in the Uzbek language. In addition, the authors also conducted an analysis of existing works, as well as a comparative analysis, which will help to identify the distinctive features and novelty of the proposed work. Moreover, in conclusion, the authors propose possible scenarios for the development of the work, in the form of further scaling of the dataset, as well as the use of other neural network architectures.

13 May 2024
Verified
Conference Paper
Closed access
DMDavlatyor Mengliev
Davlatyor Mengliev
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
VBVladimir Barakhnin
Vladimir Barakhnin
RARuslan Abdullayev
Ruslan Abdullayev
NBNodirbek Boltayev
Nodirbek Boltayev
BIBahodir Ibragimov
Bahodir Ibragimov
This article discusses an original approach to calculating the TF-IDF metric for Karakalpak language documents. The paper reviews related work, including efforts to automatically extract stop words and apply the TF-IDF metric tailored to the linguistic characteristics of the Karakalpak language, highlighting the importance of morphological preprocessing to improve the accuracy and efficiency of algorithms.Despite the challenges associated with the agglutinative nature of the Karakalpak language, such as the need for extensive morphological pre-processing to accurately identify and analyze word forms, this study proposes a new algorithm that demonstrates significant potential in dealing with the complexity of the language. By carefully adapting the TF-IDF metric to account for the morphological structure of Karakalpak, the proposed algorithm marks a significant advance in the computational analysis of agglutinative languages.Testing of the algorithm was thorough and included a diverse set of words unique to each dialect, as well as words common to multiple dialects and misspelled words. The algorithm has demonstrated high accuracy in identifying dialect-specific words and processing records in mixed dialects.In addition, this study contributes to the broader field of Turkic languages by offering insights into the structural and lexical features of the Uzbek language.

30 September 2024
Verified
Conference Paper
Closed access
Davlatyor MenglievDavlatyor Mengliev
Davlatyor Mengliev
Vladimir BarakhninVladimir Barakhnin
Vladimir Barakhnin
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
OAOybek T. Allamov
Oybek T. Allamov
BIBahodir B. Ibragimov
Bahodir B. Ibragimov
TKTimur A. Khudaybergenov
Timur A. Khudaybergenov
In this study, the authors propose an algorithm for recognizing legal documents in Karakalpak texts. To develop such an algorithm, similar scientific works were studied, the relevance of the current work and the problems that need to be solved were identified. The proposed algorithm is developed based on traditional rules, which include the rules of morphology of the Karakalpak language, as well as a dictionary of tagged words used to identify legal words and phrases from texts. The dictionary used contains more than 12,000 tagged words, which include both word roots and other forms concatenated to grammatical affixes. The authors also tested the algorithm, where high accuracy in identifying the necessary words was achieved. In particular, three samples were formed, each of which contained words and phrases of legal terminology in a certain amount. In conclusion, the authors added information regarding the proposed improvements and further prospects for the development of the algorithm.

1 January 2024 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
PDF file
Davlatyor MenglievDavlatyor Mengliev
Davlatyor Mengliev
Vladimir BarakhninVladimir Barakhnin
Vladimir Barakhnin
ASAzizbek Sultonboyev
Azizbek Sultonboyev
BIBahodir Ibragimov
Bahodir Ibragimov
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
RARuslan Abdullayev
Ruslan Abdullayev
This article presents an original approach to recognizing named entities in Karakalpak language texts. The approach involves the author’s algorithm, which uses This article presents an original approach to recognizing named entities in Karakalpak language texts. The approach involves the author’s algorithm, which uses

10 November 2023
Verified
Conference Paper
Closed access
DMDavlatyor B. Mengliev
Davlatyor B. Mengliev
VBVladimir B. Barakhnin
Vladimir B. Barakhnin
MAMukhammadjon Atakhanov
Mukhammadjon Atakhanov
BIBahodir B. Ibragimov
Bahodir B. Ibragimov
Mukhriddin EshkulovMukhriddin Eshkulov
Mukhriddin Eshkulov
BSBobur Saidov
Bobur Saidov
Named entity recognition is one of the current problems in the field of natural language processing, especially for languages with limited resources, where the Uzbek language is one of them. In this scientific work, the authors conduct a review study and also propose a practical solution for recognizing named entities in the Uzbek language. The proposed approach is designed and operated on the basis of gazetteer rules and lists, with special emphasis on the identification of place names. The authors do not use machine learning methods due to limited linguistic resources, which makes the proposed approach easy to implement and fast to scale.The cornerstone of the proposed approach is two algorithms, where the first algorithm, based on morphological analysis, despite its simplicity, is somewhat limited in its capabilities. Conversely, the second algorithm is based on the syntactic analysis of texts in the Uzbek language and offers a more flexible approach to recognizing named entities.Both algorithms use a specific set of rules obtained as a result of a detailed study of the structure of the Uzbek language and its morphological and grammatical features.The purpose of this study is to enrich the relatively sparse literature on named entity recognition in the Uzbek language and to provide a solid basis for continued research in this area.