IDEAS home Printed from https://ideas.repec.org/h/spr/prbchp/978-3-031-88052-0_19.html
   My bibliography  Save this book chapter

Advancing Machine Comprehension of the Georgian Language

In: Digital Management and Artificial Intelligence

Author

Listed:
  • Tea Munjishvili

    (Tbilisi State University)

  • Teona Shugliashvili

    (Ludwig Maximilian University of Munich)

Abstract

The complexity of the Georgian language poses challenges for machines. AI efforts, like Schmidt’s (2019) use of POS tagging with Bi-LSTMs and AI Translate chatbots, aim to teach machines Georgian. Integration of Georgian Language into models like ChatGPT, using NLP techniques and diverse machine learning models, has occurred, but outcomes have limitations. Companies pay money for premium access to ChatGPT, While many companies invest in premium access to ChatGPT, its performance can vary across languages. In the case of Georgian, the model might occasionally lack precision due to limited training data. In this paper we outline our AI strategy to enhance machine understanding of Georgian language. Our unique method, “predictive grammar” tackles the limitations of reliance on statistical patterns. It combines semantic analysis algorithms with beyond-system engineering techniques grounded in the axiom: “Rules for understanding semantics in each problem area can be detected to develop a model of logical-probability semantics.” To determine if a candidate sentence conveys the same meaning as a unique sentence or bag-of-words from the knowledge base, we First, analyze the influence of each word in the candidate sentence on the knowledge base of the unique sentence by calculating multiple information indices. Next, we construct a logical-probability semantic model and establish semantic connections using these influence measures. The meaning of the candidate sentence is derived from these semantic connections. We identify each sentence corresponding to the unique sentence or bag-of-words by understanding its meaning and matching it with the candidate sentences. This process is detailed in Munjishvili et al. (2023). Over 11 years, its application across diverse fields, from digital health to financial analytics, “predictive grammar” method showcases the robustness, with no instances of miscomprehension recorded. Machine Understanding of the Georgian Language has wide applications in digital management, spanning business intelligence, data management, CRM, chatbots, content management, customer behavior research, education, supply chain, and human resources. It’s beneficial for data-driven AI systems, improving decision-making, automating tasks, enhancing customer interactions, and optimizing digital content and resource management.

Suggested Citation

  • Tea Munjishvili & Teona Shugliashvili, 2025. "Advancing Machine Comprehension of the Georgian Language," Springer Proceedings in Business and Economics, in: Richard C. Geibel & Shalva Machavariani (ed.), Digital Management and Artificial Intelligence, pages 243-251, Springer.
    • Handle: RePEc:spr:prbchp:978-3-031-88052-0_19
    DOI: 10.1007/978-3-031-88052-0_19
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:prbchp:978-3-031-88052-0_19. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.