التعلم الآلي و استخراج البيانات الببليوجرافية من المواد النصية : نموذج مقترح للمواد النصية باللغة العربية

الملخص EN

In recent times, the term artificial intelligence and its various applications have spread, such as machine learning, deep learning, natural language processing, and computer vision, and it has been used in many sectors and has resulted in business development in terms of performance, speed and quality.

This development has also extended to libraries and information centers as one of the largest institutions that provide knowledge services, and the research sheds light on the process of extracting bibliographic data from information sources, especially text materials that include (books and scientific articles), Where the search is to encourage enterprises and institutions of information industry knowledge, namely publishers, libraries and information centers to adopt the use of bibliographic data extraction tools, The proposed model provides a general framework for extracting bibliographic data from information sources - text -Arabic, And to facilitate catalogers works and not cancel their role fully, Although the technology could limit the role of the catalogers, The research provides an explanation of what artificial intelligence is and its applications, And the definition of what is descriptive cataloging, clarifying the role of the publisher in the process of creating bibliographic records, and making use of the capabilities of machine learning in extracting bibliographic data from textual information sources, in addition to presenting the structure and components of the proposed model for extracting bibliographic data out of a number of results and recommendations.