Application of NLP models to Extract Pricing Information from Unstructured Dialogues
( Pp. 182-193)

Goal. This article discusses the theoretical and practical aspects of applying natural language processing (NLP) models in business processes of organizations of various scales. The purpose of the research is to systematize and analyze the main directions of NLP models application in modern business, as well as to develop practical recommendations for their effective implementation. Model. The research is based on the work of foreign authors who conceptually studied the application of NLP models in relation to various business processes. The research methodology is based on a systematic analysis of scientific publications and industry reports, a comparative analysis of technological solutions and a structural and functional approach to the systematization of NLP applications. Conclusions. The analysis of the main tasks solved using NLP models in business is carried out, among which are the generation of text content, text classification, automation of customer support, information summarization, machine translation and personalization of marketing interaction. The technological pipeline for creating and training NLP models is studied with a detailed examination of tokenization processes, vector representation of data, and the application of the attention mechanism. The research results demonstrate the high potential of NLP technologies for optimizing business processes. It has been revealed that, despite the growing interest in these technologies, their full-fledged implementation into the business processes of domestic companies remains limited. Practical significance. Practical recommendations on a strategic approach to the implementation of NLP technologies are formulated, including step-by-step integration with measurable results, focus on solving specific business problems and the need for investments in staff training. An example of the application of the model to solve the problem of extracting information from text in Russian is shown. Social consequences. The widespread introduction of NLP technologies in business leads to significant changes in the employment structure, requiring the retraining of specialists and the creation of new competencies in the labor market. Originality/value. The study is valuable for business leaders, IT specialists and digital transformation specialists, and offers a comprehensive analysis of the possibilities of using NLP technologies in various sectors of the economy. The novelty of the work lies in the systematization of NLP models in business, taking into account Russian specifics and current market trends.

Bokarev D.V., Nikishov S.I. Application of NLP models to Extract Pricing Information from Unstructured Dialogues. Computational Nanotechnology. 2025. Vol. 12. No. 1. Pp. 182–193. (In Rus.). DOI: 10.33693/2313-223X-2025-12-1-182-193. EDN: NDXMJR

Atoev V.V., Chuvenkov A.F. Application of artificial intelligence technologies to analyze customer satisfaction in the field of food delivery. In: Scientific vector: Collection of scientific works. Rostov-on-Don: Rostov State University of Economics “RINH”, 2024. Pp. 304–306. EDN: NVZEPI.
Batishchev A.V., Mamedov R.S., Kondratenko N.A., Volkov A.A. Achieving business goals through the use of NLP. Natural-humanitarian Studies. 2023. No. 6 (50). Pp. 596–600. (In Rus.). EDN: PGNTXJ.
Martynova I.R., Platonov E.N. Semantic analysis of reviews about organizations using machine learning methods. Modeling and Data Analysis. 2024. Vol. 14. No. 1. Pp. 7–26. (In Rus.). DOI: 10.17759/mda.2024140101. EDN: FWXPLF.
Rogatkin A.V. The use of artificial intelligence technologies to automate customer service processes and improve the quality of service. Bakery of Russia. 2024. Vol. 68. No. 2. Pp. 100–107. (In Rus.). EDN: OGCJXG.
Arif W. Leveraging Natural Language Processing (NLP) for automated customer support systems. 2024. URL: https://www.researchgate.net/publication/384678656_Leveraging_Natural_Language_Processing_NLP_for_Automated_Customer_Support_Systems
Bahja M. Natural Language Processing applications in business. 2021. DOI: 10.5772/intechopen.92203. URL: https://www.intechopen.com/chapters/71990
Cappel J., Chasin F. Bridging enterprise knowledge management and Natural Language Processing – integration framework and a prototype. In: Design Science research for a resilient future. Proceedings of 19th International Conference on Design Science Research in Information Systems and Technology, DESRIST 2024 (Trollhättan, Sweden, June 3–5, 2024). 2024. Pp. 278–294. DOI: 10.1007/978-3-031-61175-9_19.
Collobert R., Weston J. A unified architecture for natural language processing: Deep neural networks with multitask learning. In: Proceedings of the 25th international conference on machine learning. 2008. Pp. 160–167.
Devlin J., Chang M.W., Lee K., Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2019. Pp. 4171–4186.
Fisher I.E., Garnsey M.R., Hughes M.E. Natural language processing in accounting, auditing and finance: A synthesis of the literature with a roadmap for future research. Intelligent Systems in Accounting, Finance and Management. 2016. No. 23 (3). Pp. 157–214.
Følstad A., Nordheim C.B., Bjørkli C.A. What makes users trust a chatbot for customer service? An exploratory interview study. In: International Conference on Internet Science. 2018. Pp. 194–208.
Howard J., Ruder S. Universal language model fine-tuning for text classification. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2018. Pp. 328–339.
Hutchins J. Machine translation: Past, present, future. N.Y.: Ellis Horwood, 1986. 382 p. (Ellis Horwood Series in Computers and their Applications)
Jelinek F. Self-organized language modeling for speech recognition. In: Readings in speech recognition. 1990. Pp. 450–506.
Liu Y., Ott M., Goyal N. et al. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692. 2019.
Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. 2013.
Pennington J., Socher R., Manning C.D. GloVe: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 2014. Pp. 1532–1543.
Sintoris K., Vergidis K. Extracting business process models using Natural Language Processing (NLP) techniques. 2017. Pp. 135–139. DOI: 10.1109/CBI.2017.41.
Turing A.M. Computing machinery and intelligence. Mind. 1950. No. 59 (236). Pp. 433–460.
Vaswani A., Shazeer N., Parmar N. et al. Attention is all you need. In: Advances in neural information processing systems. 2017. Pp. 5998–6008.

artificial intelligence, small and medium-sized businesses, NLP in business, natural language processing, market.