Abstract
A growing trend in computer interaction approaches is human-computer interaction, which describes communication between a person and a computer and is known as a chatbot. A conversational agent, often known as a chatbot, is a computer program that attempts to provide responses that appear human during a conversation. Studies on several chatbot applications, are been carried out in this research on the areas of Natural Language Processing (NLP), the Natural Language understanding (NLU), and Intent recognition in recent years. There are several NLU applications in various fields, including Chatbots, search in natural language, voice-driven assistants, web- scale information extraction, legal discovery, and content summarization. Intent classification is one of the biggest challenges in NLP. Some of the chatbots classifies students requests to make them simpler to comprehend. A chatbot is an appliance of software that replicates and processes human communication to offer real-time digital assistance. Various tasks that were previously handled by human agents, like assistance to customers, medical counselling, digital commerce and issues addressing, are now being assigned to chatbots. Due to the appearance of machine learning techniques, the main step in chatbot development was defining the rules that would be used to create responses. Here are some strategies for chatbot applications and the machine-learning techniques that underpin them.
References
M. Li, S.J. Liu, D.D. Zhang, M. Zhou, Machine Translation. Beijing: Higher Education Press, 2018.
Y. Wang, “Natural language processing and applications in machine learning,” Modern Chinese, vol. 5, pp.187-191, 2019.
Y. Bar-Hillel, “The present status of automatic translation of languages,” Advances in Computers, vol.1, pp.91-163, 1960.
“Machine learning: Algorithms and applications-researchgate.” Available:https://www.researchgate.net/publication/303806260_Machine_Learning_Algorithms_and_Applica tions.
Zini, Julia El, and Mariette Awad. "On the explainability of natural language processing deep models." ACM Computing Surveys 55.5 (2022): 1-31.
Masche, J., Le, NT. (2018). A Review of Technologies for Conversational Systems. In: Le, NT., van Do, T., Nguyen, N., Thi, H. (eds) Advanced Computational Methods for Knowledge Engineering. ICCSAMA 2017. Advances in Intelligent Systems and Computing, vol 629. Springer, Cham.https://doi.org/10.1007/978-3-319-61911-8_19
Arsovski, S., Muniru, I., & Cheok, A. (2017). Analysis of the chatbot open source languages aiml and chatscript: A review. http://dx.doi.org/10.13140/RG.2.2.34160.15367.
N. T. Thomas, "An e-business chatbot using AIML and LSA," 2016 International Conference on Advances in Computing,Communications and Informatics (ICACCI), Jaipur, India, 2016, pp. 2740- 2742, doi: 10.1109/ICACCI.2016.7732476.
PanelEleni Adamopoulou and Abstract This literature review presents the History, “Chatbots: History, technology, and applications,” Machine Learning with Applications, 09-Nov-2020.[Online]. Available: https://www.sciencedirect.com/science/article/pii/S2666827020300062.
Ramesh, K., Ravishankaran, S., Joshi, A., Chandrasekaran, K. (2017). A Survey of Design Techniques for Conversational Agents. In: Kaushik, S., Gupta, D., Kharb, L., Chahal, D. (eds) Information, Communication and Computing Technology. ICICCT 2017. Communications in Computer and Information Science, vol 750.Springer, Singapore. https://doi.org/10.1007/978-981-10-6544-6_31
Nahdatul Akma Ahmad, Mohamad Hafiz Che Hamid, Azaliza Zainal, Muhammad Fairuz Abd Rauf, and Zuraidy Adnan, “(PDF) review of Chatbots Design Techniques - Researchgate,” 08-Aug-2018. https://www.researchgate.net/publication/327097910_Review_of_Chatbots_Design_Techniques.
Juanan Pereira and Oscar Díaz, “A quality analysis of Facebook Messenger's most popular chatbots,” Apr-2018. https://www.researchgate.net/publication/324562033_A_quality_analysis_of_Facebook_Messeng er's_most_popular_chatbots.
S. Shum, H. He, H. Li, Xd. & Li, and D., “From Eliza to xiaoice: Challenges and opportunities with social chatbots - frontiers of information technology & electronic engineering,” SpringerLink, 08- Jan-2018. Available: https://link.springer.com/article/10.1631/FITEE.1700826.
M. Sathvik, “Enhancing machine learning algorithms using GPT embeddings for binary classification,” figshare, 27-Mar-2023.[Online]. Available: https://www.techrxiv.org/articles/preprint/Enhancing_Machine_Learning_Algorithms_using_GPT_ Embeddin gs_for_Binary_Classification/22331053.
T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan,P. Shyam, G. Sastry, A.Askell, S. Agarwal, A. Herbert-Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, “Language modelsare few-shot learners,” arXiv.org, 22-Jul-2020. Available: https://arxiv.org/abs/2005.14165.
Iryna Pentina, Tyler Hancock, and Tianling Xie, “Exploring relationship development with social chatbots: A mixed-method study of replika,” Computers in Human Behavior.140.107600.10.1016/j.chb.2022.107600.,Dec-2022. https://www.researchgate.net/publication/366068126_Exploring_relationship_development_with_s ocial_chatbots_A_mixed-method_study_of_replika.
Timm Teubner, Christoph M. Flath, Christof Weinhardt, Wil van der Aalst, and Oliver Hinz, “Welcome to the era of chatgpt et al. -springer,”13-Mar-2023. Available: https://link.springer.com/content/pdf/10.1007/s12599-023-00795-x.pdf.
https://www.taus.net/resources/blog/intent-recognition-in-nlp