DSpace JSPUI
DSpace зберігає і дозволяє легкий і відкритий доступ до всіх видів цифрового контенту, включаючи текст, зображення, анімовані зображення, MPEG і набори даних
Дізнатися більше
Будь ласка, використовуйте цей ідентифікатор, щоб цитувати або посилатися на цей матеріал:
http://ds.knu.edu.ua/jspui/handle/123456789/9262| Назва: | Bibliometric analysis and experimental assessment of chatbot training approaches |
| Автори: | Liashenko, Roman O. Semerikov, Serhiy O. |
| Ключові слова: | chatbot natural language processing bibliometric analysis transfer learning GPT-2 |
| Дата публікації: | 7-лют-2025 |
| Видавництво: | CEUR Workshop Proceedings |
| Бібліографічний опис: | Bibliometric analysis and experimental assessment of chatbot training approaches / Roman O. Liashenko, Serhiy O. Semerikov // Proceedings of the 7th Workshop for Young Scientists in Computer Science & Software Engineering (CS&SE@SW 2024). Virtual Event, Kryvyi Rih, Ukraine, December 27, 2024 / Edited by: Serhiy O. Semerikov, Andrii M. Striuk // CEUR Workshop Proceedings. – 2025. – Vol. 3917. – P. 199-225. – Access mode : https://ceur-ws.org/Vol-3917/paper58.pdf DOI: https://doi.org/10.55056/ceur-ws.org/Vol-3917/paper58.pdf |
| Короткий огляд (реферат): | The rapid development of natural language processing and artificial intelligence has led to growing interest in creating chatbots capable of engaging in human-like dialogue. This study conducts a bibliometric analysis of research on chatbot training to identify key concepts, trends, and promising directions. The analysis of 549 publications from the Scopus database using VOSviewer reveals four main clusters of research: natural language processing techniques, application of NLP technologies in society, use of machine learning for NLP, and chatbots in education and service sectors. To experimentally evaluate chatbot training approaches, two datasets are created from scientific publications and used to fine-tune GPT-2 language models. The results demonstrate the feasibility and effectiveness of transfer learning for adapting pre-trained models to domain-specific data. This research provides insights into the state-of-the-art in chatbot development and highlights opportunities for future work on creating specialized conversational agents. |
| Опис: | [1] G. M. Franklin, Google’s new AI Chatbot produces fake health-related evidence-then self-corrects, PLOS Digital Health 3 (2024) 1–4. doi:10.1371/journal.pdig.0000619. [2] A. G. Usigan, M. I. Salomeo, G. J. L. J. Zafe, C. J. Centeno, A. A. R. C. Sison, A. G. Bitancor, Implementation of an Undergraduate Admission Chatbot Using Microsoft Azure’s Question Answering and Bot Framework, in: Proceedings of the 2022 5th Artificial Intelligence and Cloud Computing Conference, AICCC ’22, Association for Computing Machinery, New York, NY, USA, 2023, p. 240–245. doi:10.1145/3582099.3582135. [3] R. Thamilselvan, P. Natesan, A. Manimaran, S. E. Naveenkumar, J. K. Shanthosh, S. Vigneshwaran, Designing A Llama 2-Powered Chatbot for Enhanced College Website Support, in: 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024, pp. 1–6. doi:10.1109/ICCCNT61001.2024.10725472. [4] A. D. Workman, V. K. Rathi, D. K. Lerner, J. N. Palmer, N. D. Adappa, N. A. Cohen, Utility of a LangChain and OpenAI GPT-powered chatbot based on the international consensus statement on allergy and rhinology: Rhinosinusitis, International Forum of Allergy & Rhinology 14 (2024) 1101–1109. doi:10.1002/alr.23310. [5] OpenAI, Introducing ChatGPT, 2022. URL: https://openai.com/blog/chatgpt. [6] S. V. Symonenko, N. V. Zaitseva, V. V. Osadchyi, K. P. Osadcha, V. S. Kruglyk, S. O. Sysoieva, Application of chatbots for enhancing communication skills of IT specialists, Journal of Physics: Conference Series 2871 (2024) 012026. doi:10.1088/1742-6596/2871/1/012026. [7] A. V. Riabko, T. A. Vakaliuk, O. V. Zaika, R. P. Kukharchuk, V. V. Kontsedailo, Chatbot algorithm for solving physics problems, CEUR Workshop Proceedings 3553 (2023) 75–92. [8] I. Mintii, S. Semerikov, Optimizing Teacher Training and Retraining for the Age of AI-Powered Personalized Learning: A Bibliometric Analysis, in: E. Faure, Y. Tryus, T. Vartiainen, O. Danchenko, M. Bondarenko, C. Bazilo, G. Zaspa (Eds.), Information Technology for Education, Science, and Technics, volume 222 of Lecture Notes on Data Engineering and Communications Technologies, Springer Nature Switzerland, Cham, 2024, pp. 339–357. doi:10.1007/978-3-031-71804-5_23. [9] R. Liashenko, S. Semerikov, The Determination and Visualisation of Key Concepts Related to the Training of Chatbots, in: E. Faure, Y. Tryus, T. Vartiainen, O. Danchenko, M. Bondarenko, C. Bazilo, G. Zaspa (Eds.), Information Technology for Education, Science, and Technics, volume 222 of Lecture Notes on Data Engineering and Communications Technologies, Springer Nature Switzerland, Cham, 2024, pp. 111–126. doi:10.1007/978-3-031-71804-5_8. [10] R. Liashenko, S. Semerikov, Bibliometric analysis of chatbot training research: Key concepts and trends, Information Technologies and Learning Tools 101 (2024) 181–199. doi:10.33407/itlt.v101i3.5622. [11] DeepLearning.AI, Search | The Batch | AI News & Insights, 2023. URL: https://www.deeplearning.ai/search/. [12] Big Bot Makes Small Talk: A research summary of Facebook’s Generative BST chatbot, 2020. URL: https://www.deeplearning.ai/the-batch/big-bot-makes-small-talk/. [13] Bot Comic: How Google’s Meena chatbot developed a sense of humor, 2020. URL: https://www.deeplearning.ai/the-batch/bot-comic/. [14] Chatbots for Productivity: Microsoft extends Copilot to 365 and Windows, 2023. URL: https://www.deeplearning.ai/the-batch/microsoft-extends-copilot-365-windows/. [15] China Chases Chatbots: Chinese tech companies race to cash in on ChatGPT fever, 2023. URL: https://www.deeplearning.ai/the-batch/chinese-tech-companies-race-to-cash-in-on-chatgpt-fever/. [16] Search War! Google and Microsoft both announce AI-Powered search, 2023. URL: https://www.deeplearning.ai/the-batch/google-and-microsoft-both-announce-ai-powered-search/. [17] Chatbots Disagree on Covid-19: Medical chatbots offered conflicting Covid advice, 2020. URL: https://www.deeplearning.ai/the-batch/chatbots-disagree-on-covid-19/. [18] Language Models, Extended: Large language models grew more reliable and less biased in 2022, 2022. URL: https://www.deeplearning.ai/the-batch/language-models-grew-more-reliable-and-less-biased-in-2022/. [19] Cost Containment for Generative AI: Microsoft’s quest to reduce the size and cost of language models, 2023. URL: https://www.deeplearning.ai/the-batch/microsofts-quest-to-reduce-the-size-and-cost-of-language-models/. [20] What We Know — and Don’t Know — About Foundation Models: A new Stanford index to assess the transparency of leading AI models, 2023. URL: https://www.deeplearning.ai/the-batch/a-new-stanford-index-to-assess-the-transparency-of-leading-ai-models/. [21] Elsevier B.V., Scopus - Document search | Signed in, 2023. URL: https://www.scopus.com/search/form.uri?display=basic#basic. [22] N. J. Van Eck, L. Waltman, VOSviewer Manual, Universiteit Leiden, 2023. URL: https://www.vosviewer.com/documentation/Manual_VOSviewer_1.6.20.pdf. [23] Centre for Science and Technology Studies, Leiden University, The Netherlands, VOSviewer - Visualizing scientific landscapes, 2023. URL: https://www.vosviewer.com/. [24] S. P. Uprety, S. R. Jeong, The Impact of Semi-Supervised Learning on the Performance of Intelligent Chatbot System, Computers, Materials & Continua 71 (2022) 3937–3952. doi:10.32604/cmc.2022.023127. [25] S. Patil, V. Mudaliar, P. Kamat, LSTM based Ensemble Network to enhance the learning of Longterm Dependencies in Chatbot, International Journal of Automation and Smart Technology 12 (2022) 2286–2286. doi:10.5875/ausmt.v12i1.2286. [26] Z. Ji, A Multi-modal Seq2seq Chatbot Framework, in: Z. Qian, M. Jabbar, X. Li (Eds.), Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications, Springer Nature, Singapore, 2022, pp. 225–233. doi:10.1007/978-981-19-2456-9_24. [27] P. Anki, A. Bustamam, H. S. Al-Ash, D. Sarwinda, Intelligent Chatbot Adapted from Question and Answer System Using RNN-LSTM Model, Journal of Physics: Conference Series 1844 (2021) 012001. doi:10.1088/1742-6596/1844/1/012001. [28] D. Dharrao, S. Gite, TherapyBot: a chatbot for mental well-being using transformers, International Journal of Advances in Applied Sciences 13 (2024) 1–12. doi:10.11591/ijaas.v13.i1.pp1-12. [29] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin, Attention Is All You Need, 2023. arXiv:1706.03762. [30] M. Lee, A Mathematical Investigation of Hallucination and Creativity in GPT Models, Mathematics 11 (2023) 2320. doi:10.3390/math11102320. [31] A. Kansal, Finetuning: The Theory, in: Building Generative AI-Powered Apps: A Hands-on Guide for Developers, Apress, Berkeley, CA, 2024, pp. 77–100. doi:10.1007/979-8-8688-0205-8_5. [32] P. Christiano, J. Leike, T. B. Brown, M. Martic, S. Legg, D. Amodei, Deep reinforcement learning from human preferences, 2023. arXiv:1706.03741. [33] T.-L. Chou, Y.-L. Hsueh, A Task-oriented Chatbot Based on LSTM and Reinforcement Learning, in: Proceedings of the 2019 3rd International Conference on Natural Language Processing and Information Retrieval, NLPIR ’19, Association for Computing Machinery, New York, NY, USA, 2019, p. 87–91. doi:10.1145/3342827.3342844. [34] Q.-D. L. Tran, A.-C. Le, V.-N. Huynh, Enhancing Conversational Model With Deep Reinforcement Learning and Adversarial Learning, IEEE Access 11 (2023) 75955–75970. doi:10.1109/ACCESS.2023.3297652. [35] R. Liashenko, S. Semerikov, Training Specialised Chatbots on Ukrainian Scientific Text Corpora Using Transfer Learning, in: 2024 IEEE 18th International Conference on Computer Science and Information Technologies (CSIT), IEEE, 2025 (in press). [36] V. Ilievski, C. Musat, A. Hossman, M. Baeriswyl, Goal-oriented chatbot dialog management bootstrapping with transfer learning, in: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, International Joint Conferences on Artificial Intelligence Organization, 2018, pp. 4115–4121. doi:10.24963/ijcai.2018/572. [37] T. Taulli, AI-Assisted Programming: Better Planning, Coding, Testing, and Deployment, O’Reilly Media, Inc., Sebastopol, CA, 2024. URL: https://www.oreilly.com/library/view/ai-assisted-programming/9781098164553/. [38] OpenAI, Fine-tuning - openai api, 2024. URL: https://platform.openai.com/finetune.[39] Google, Google ai studio, 2024. URL: https://aistudio.google.com/. [40] Google, Available regions for Google AI Studio and Gemini API, 2024. URL: https://ai.google.dev/gemini-api/docs/available-regions. [41] S. Elaprolu, Introducing the AWS Generative AI Innovation Center’s Custom Model Program for Anthropic Claude, 2023. URL: https://aws.amazon.com/blogs/machine-learning/introducing-the-aws-generative-ai-innovation-centers-custom-model-program-for-anthropic-claude/. [42] A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, Language Models are Unsupervised Multitask Learners, 2019. URL: https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf. [43] A. W. Ohlheiser, K. Hao, An AI is training counselors to deal with teens in crisis, 2021. URL: https://www.technologyreview.com/2021/02/26/1020010/trevor-project-ai-suicide-hotline-training/. |
| URI (Уніфікований ідентифікатор ресурсу): | https://ceur-ws.org/Vol-3917/paper58.pdf http://ds.knu.edu.ua/jspui/handle/123456789/9262 |
| ISSN: | 1613-0073 |
| Розташовується у зібраннях: | Кафедра професійної та соціально-гуманітарної освіти |
Файли цього матеріалу:
| Файл | Опис | Розмір | Формат | |
|---|---|---|---|---|
| paper58.pdf | 2.63 MB | Adobe PDF | Переглянути/Відкрити |
Усі матеріали в архіві електронних ресурсів захищені авторським правом, всі права збережені.