Reverse synthesis of natural language phrases grounding on their ontological representation using a large language model

• Published in: PROBLEMS IN PROGRAMMING
• Date: 2024
• Issue: 2-3
• Pages: 359-366
• ISSN: 1727-4907
• Author Affiliations: V.V. Kaverynskyi — Glushkov Institute of Cybernetics NAS of Ukraine; A.A. Litvin — Glushkov Institute of Cybernetics NAS of Ukraine; O.V. Palagin — Glushkov Institute of Cybernetics NAS of Ukraine
• Keywords: векторні представлення слів, оцінка близькості-зв’язності слів природної мови, large language models, велика мовна модель, small language models, штучний інтелект ші, семантичне представлення речень, векторизація тексту, великі мовні моделі llm, аналіз природньої мови
• Main Authors: Kaverynskyi, V.V., Litvin, A.A., Palagin, O.V.
• Format: Article
• Language: Ukrainian
• Published: PROBLEMS IN PROGRAMMING 2024
• Subjects: large language model; ontology; natural language text synthesis; natural language text analysis; cosine similarity; text vectorization; UDC 004.724; 004.62
• Online Access: https://pp.isofts.kiev.ua/index.php/ojs1/article/view/657
• Journal Title: Problems in programming

The presented article introduces a novel solution that uses a specially developed structured prompt for a large language model (Chat GPT). A series of experiments were carried out on synthesizing natural language phrases based on their ontological representations. These ontological representations w...