KAM RESURSLI TILLARDAGI ILMIY JURNALLAR UCHUN METAMA’LUMOTLARNI AVTOMATIK EKSTRAKSIYA QILISH VOSITASI
DOI:
https://doi.org/10.5281/zenodo.22281420Abstract
Ilmiy jurnallarni raqamlashtirish va ularni Open Journal Systems (OJS) kabi elektron platformalarga o‘tkazish
jarayonida tahririyat xodimlari va kutubxonachilar oldida turgan asosiy muammolardan biri — har bir maqola uchun
bibliografik metama’lumotlarni (sarlavha, mualliflar, annotatsiya, kalit so‘zlar) qo‘lda kiritishning yuqori vaqt va mehnat
sarfini talab qilishidir. Bu muammo, ayniqsa, o‘zbek, rus va boshqa kam resursli tillarda nashr etiladigan jurnallar uchun
yanada keskinlashadi, chunki GROBID yoki CERMINE kabi xalqaro darajada tan olingan avtomatik ekstraksiya tizimlari
asosan ingliz tilidagi yirik korpuslar asosida o‘qitilgan bo‘lib, mahalliy tillardagi nashrlar bilan ishlashda ishonchliligi pasayadi.
Ushbu maqolada texnik mutaxassis bo‘lmagan tahririyat xodimi yoki kutubxonachi tomonidan ham qo‘llanilishi
mumkin bo‘lgan MetaExtract nomli dasturiy vositaning ish tamoyili va amaliy joriy etish jarayoni tavsiflanadi. Vosita foydalanuvchidan
faqat jurnalning bitta namunaviy sonini bir marta “belgilashni” talab qiladi, so‘ngra hosil bo‘lgan qoidalar
shu jurnalning istalgan miqdordagi qolgan maqolalarini avtomatik qayta ishlash uchun qayta-qayta ishlatiladi va natijalar
to‘g‘ridan-to‘g‘ri OJS tizimiga import qilinadigan XML formatida chiqariladi. Maqolada vositaning kutubxona-tahririyat
amaliyotidagi o‘rni, uni joriy etish bosqichlari va uning institutsional repozitoriylar samaradorligiga ta’siri muhokama
qilinadi.
Keywords
metama’lumotlarni avtomatik ekstraksiya qilish; ilmiy jurnallarni raqamlashtirish; Open Journal Systems; institutsional repozitoriy; kam resursli tillar; tahririyat ish jarayoniReferences
Tkaczyk D, Szostek P, Fedoryszak M, Dendek PJ, Bolikowski Ł. CERMINE: automatic extraction of structured metadata
from scientific literature. International Journal on Document Analysis and Recognition (IJDAR). 2015 Dec;18(4):317-
Kong H, Yoon H, Seol J, Hyun M, Lee H, Kim S, Choi W. Annotated open corpus construction and BERT-based
approach for automatic metadata extraction from Korean academic papers. IEEE Access. 2022 Dec 29;11:825-38.
Ahmed MW, Afzal MT. FLAG-PDFe: Features oriented metadata extraction framework for scientific publications. IEEE
Access. 2020 May 27;8:99458-69.
Skluzacek TJ, Chard K, Foster I. Automated metadata extraction: challenges and opportunities. In2022 IEEE 18th
International Conference on e-Science (e-Science) 2022 Oct 11 (pp. 495-500). IEEE.
Suryani MA, Hahne S, Beth C, Wallmann K, Renz M. DAF: Data Acquisition Framework to Support Information
Extraction from Scientific Publications. InKDIR 2023 (pp. 468-476).
Hashmi AM, Afzal MT, ur Rehman S. Rule based approach to extract metadata from scientific PDF documents. In2020
th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)
Nov 25 (pp. 1-4). IEEE.
Alamoudi A, Alomari A, Alwarthan S. A rule-based information extraction approach for extracting metadata from PDF
books. ICIC Express Letters, Part B: Applications. 2021 Feb;12(2):121-32.
Raval P, Bhaidasna H. Metadata Extraction From Scholarly Document Using Deep Learning. In2025 3rd International
Conference on Inventive Computing and Informatics (ICICI) 2025 Jun 4 (pp. 1-5). IEEE.
Ingram WA, Wu J, Kahu SY, Manzoor JA, Banerjee B, Ahuja A, Choudhury MH, Salsabil L, Shields W, Fox EA. Building
datasets to support information extraction and structure parsing from electronic theses and dissertations. International
Journal on Digital Libraries. 2024 Jun;25(2):175-96.
Skluzacek TJ, Chen M, Hsu E, Chard K, Foster I. Models and metrics for mining meaningful metadata. InInternational
Conference on Computational Science 2022 Jun 15 (pp. 417-430). Cham: Springer International Publishing.
Boukhers Z, Bouabdallah A. Vision and natural language for metadata extraction from scientific PDF documents: A
multimodal approach. InProceedings of the 22nd ACM/IEEE Joint Conference on Digital Libraries 2022 Jun 20 (pp.
-5).
T. J. Skluzacek, “Automated metadata extraction can make data swamps more navigable,” Ph.D. dissertation, The
University of Chicago, 2022.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 MUHANDISLIK VA IQTISODIYOT
This work is licensed under a Creative Commons Attribution 4.0 International License.
