TARU PUBLICATIONS
 Journal of Statistics and Management Systems cover
Open Access ·Peer-reviewed·ISSN (Online): 2169-0014·ISSN (Print): 0972-0510
Powered by:Powered by

The Journal of Statistics and Management Systems (JSMS) is a world leading journal publishing high quality, rigorously peer-reviewed original research on theoretical and applied statistics and management systems since 1998. The scope is intentionally broad, but papers must make a novel contribution to the field to be considered for publication. Topics include, but are not limited to, the following: • Statistics • Applied Statistics • Industrial Statistics • Statistical Inference • Interdisciplinary role of Statistics • Actuarial Sciences • Decision Sciences • Managerial Aspects • Management Sciences • Management Information Systems

Issues up to 2022 co-published with and available at:Taylor & Francis Online
submissions@tarupublications.com
Open Access Research Article

Socializing NLG, NLP & NLU through AI : Real-world application and future perspectives

* , , ,

* Corresponding author · click or hover a name for details

pp. 1625–1637Vol. 28Issue 8November 2025DOI: 10.47974/JSMS-1543XML
Received:
12 Feb 2025
Published Online:
24 Nov 2025
Article type:
Research Article
Language:
EN
Article no.:
JSMS-1543
Pages:
1625–1637

Abstract

The usage of wide-ranging fields of technology has seen the inclusion of AI industries and its development with time which has allowed the industries to grow around the world. This research attempts to explain and broaden the scope of some aspects of Artificial Intelligence and in this specific case AI includes NLP, NLU and NLG. This paper starts from explaining its core components of AI, then continues with the discussion and explanation of AI architecture in the form of a visual presentation. A literature review commences with the sentiment analysis of Chat GPT 2024-2025 reviews. The analysis was demonstrated using a pie chart that represented positive, neutral and negative sentiments. Additionally, a time-distribution graph illustrates the data proves the increased use of AI over time. The paper also tackles the important barriers that stop AI from becoming the ground breaking technology. As part of the introduction, the definitions and basic prerequisites of AI, NLP, NLU and NLG will be reviewed so as to help understand their usages. In the end, the study covers the change in AI and its improvements, stressing on its integration in human involvement. The end of the paper gives suggestions as to how AI can be simplified to reach out to many people, in turn creating awareness and adoption.

Keywords

Subject Classifications

68T0168T5068T0791F2068T50

References

[1] L. Danlos and A. El Ghali, “A complete integrated NLG system using AI and NLU tools,” in Proceedings of COLING’02 (2002).
[2] C. Su, G. Tur, D. Hakkani-Tür, and L. Heck, “A re-ranker scheme for integrating large scale NLU models,” in Proc. IEEE Spoken Language Technology Workshop (SLT) (2018).
[3] W. Chen, J. Chen, H. Xiong, W. Wang, and W. Y. Wang, “Logical natural language generation from open-domain tables,” arXiv preprint arXiv:2004.10404 (2020).
[4] S. Yanouz, B. A. Abdelhakim, and M. Benhmed, “A smart chatbot architecture based on NLP and machine learning for health care assistance,” in Proc. 3rd Int. Conf. on Networking, Information Systems & Security (2020).
[5] S. Arora, P. Kumar, S. P. Singh, and R. K. Gupta, “Artificial intelligence and virtual assistant working model,” in Mobile Radio Communications and 5G Networks: Proceedings of MRCN 2020, Singapore: Springer Singapore, pp. 163–171 (2020).
[6] P. M. Mah, I. Skalna, and J. Muzam, “Natural language processing and artificial intelligence for enterprise management in the era of industry 4.0,” Applied Sciences, vol. 12, no. 18, pp. 9207 (2022).
[7] S. M. Mohammad, “Artificial intelligence in information technology,” SSRN Electronic Journal (2020). [Online]. Available: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3625444
[8] K. R. Chowdhary, “Natural language processing,” in Fundamentals of Artificial Intelligence, Springer, pp. 603–649 (2020).
[9] AI Incident Database via AI Index, “Global annual number of reported artificial intelligence incidents and controversies” [dataset], AI Incident Database via AI Index, AI Index Report, processed by Our World in Data (2024). [Online]. Available: https://ourworldindata.org/grapher/annual-reported-ai-incidents-controversies
[10] S. Gehrmann, T. Clark, E. Salesky, S. Waseem, W. X. Shi, P. Stenetorp, and D. Jurafsky, “The GEM benchmark: Natural language generation, its evaluation and metrics,” arXiv preprint arXiv:2102.01672 (2021).
[11] A. B. Saka, O. A. Oyedele, O. A. Ogunseye, and A. O. Ajayi, “Conversational artificial intelligence in the AEC industry: A review of present status, challenges and opportunities,” Advanced Engineering Informatics, vol. 55, p. 101869 (2023).
[12] M.-F. de-Lima-Santos and W. Ceron, “Artificial intelligence in news media: Current perceptions and future outlook,” Journalism and Media, vol. 3, no. 1, pp. 13–26 (2021).
[13] D. Rahmani and H. Kamberaj, “Implementation and usage of artificial intelligence powered chatbots in human resources management systems,” in Proc. Int. Conf. on Social and Applied Sciences, University of New York Tirana (2021).
[14] G. Frisoni, M. Caccia, F. Conia, A. Lenci, R. Navigli, and M. Ronzano, “NLG-Metricverse: An end-to-end library for evaluating natural language generation,” in Proc. 29th Int. Conf. on Computational Linguistics (COLING 2022) (2022).
[15] B. MacCartney, Understanding Natural Language Understanding, presented at the ACM SIGAI Bay Area Chapter Inaugural Meeting, San Mateo, CA, USA. [Online]. Available: https://www.youtube.com/watch?v=vcPd0V4VSNU
[16] K. Hamilton, T. Anderson, A. Bentz, and L. Zettlemoyer, “Is neuro-symbolic AI meeting its promises in natural language processing? A structured review,” Semantic Web Preprint, pp. 1–42 (2022).
[17] A. Nair and A. Loomba, “A study on how sentiment analysis plays a multifaceted role in customer experience with special reference to Indian fintech industry,” (2024).
[18] D.-M. Park, S.-S. Jeong, and Y.-S. Seo, “Systematic review on chatbot techniques and applications,” Journal of Information Processing Systems, vol. 18, no. 1, pp. 26–47 (2022).
[19] Y. Liu, W. Chen, Z. Liu, X. Zhang, M. Chen, and M. Sun, “GPTEval: NLG evaluation using GPT-4 with better human alignment,” arXiv preprint arXiv:2303.16634 (2023).
[20] J. Wang, Z. Wang, H. Li, Y. Liu, and X. Zhao, “Is ChatGPT a good NLG evaluator? A preliminary study,” arXiv preprint arXiv:2303.04048 (2023).
[21] H. Telychko, A. Kuzmenko, O. Vasylieva, and M. Chorna, “Personalized training with the help of automation and assistant based on artificial intelligence,” EasyChair Preprint, no. 9958 (2023).
[22] M. S. Vigil, M. S. Vineeth, A. K. Nair, and J. Thomas, “Crime information collection system using chatbot,” in AIP Conference Proceedings, vol. 2587, no. 1 (2023).
[23] A. K. Kar, P. S. Varsha, and S. Rajan, “Unravelling the impact of generative artificial intelligence (GAI) in industrial applications: A review of scientific and grey literature,” Global Journal of Flexible Systems Management, vol. 24, no. 4, pp. 659–689 (2023).
[24] R. K. Solanki, P. K. Patel, R. K. Vyas, and D. K. Patel, “Building a conversational chatbot using machine learning: Towards a more intelligent healthcare application,” in Handbook of Research on Instructional Technologies in Health Education and Allied Disciplines, IGI Global, pp. 285–309 (2023).

Views: 93Downloads: 6Citations: 0