NLP for Intelligent Conversational Assistance
Keywords:
Artificial Intelligence, Context-Centric, Humans Computer Interaction, Machine, Natural Language ProcessingAbstract
Context-specific signals were often used as extra supportive measures secondary kinds of evidence to aid interpret its user's language inputs in the early days of Natural Languages Processing (NLP). The context was employed in conversational bargaining more as tie breaking technique than as a fundamental components. Recent advances in the context based reasoning have prompted paradigm shift away from context-assisted approaches and toward context centric natural language processing system. To support today's advanced Humans Computer Interactions (HCI) application, including personal digital assistants, languages tutors, as well as questions answering system, the importance of context in NLP must evolve. There is indeed a strong feeling of utilitarian, intent communication in these apps. The underlying NLP approaches must be capable of navigating throughout a concept as well as contextual discussion with such a focus on goal-oriented behavior. The natural relationship between NLP as well as context based approaches are explored in this paper, as it shows itself in the frame of reference paradigm. The major goal of this study is to understand more about NPL technology for conversational intelligence. Along the process, insights or examples are presented to shed light on this evolving approach to natural language-based HCI architecture. Natural language processing will be able to leverage its potential for human-like speech or text interpretation in the future through a variety of applications thanks to semantic and cognitive technology.
Downloads
References
M. D. Kovacs, J. Mesterhazy, D. Avrin, T. Urbania, and J. Mongan, “Correlate: A PACS- and EHR-integrated tool leveraging natural language processing to provide automated clinical follow-up,” Radiographics. 2017, doi: 10.1148/rg.2017160195.
N. Wang and R. R. A. Issa, “Natural language generation from building information models for intelligent NLP based information extraction,” 2020.
S. J., S. Swamy, and S. C., “Survey on - Socially Intelligent
Robots by using NLP,” Int. J. Comput. Appl., 2017, doi: 10.5120/ijca2017914731.
K. Souali, O. Rahmaoui, M. Ouzzif, and I. El Haddioui, “Recommending moodle resources using chatbots,” Proc. - 15th Int. Conf. Signal Image Technol. Internet Based Syst. SISITS 2019, pp. 677–680, 2019, doi: 10.1109/SITIS.2019.00110.
L. A. Amaral and R. Ziai, “Analyzing Learner Language : Towards A Flexible NLP Architecture for Intelligent Language Tutors,” Comput. Assist. Lang. Learn., 2011.
G. Malik, D. K. Tayal, and S. Vij, “An analysis of the role of artificial intelligence in education and teaching,” in Advances in Intelligent Systems and Computing, 2019.
“A Data Product View on Conversational AI.” [8] A. Sarker, A. Z. Klein, J. Mee, P. Harik, and G. Gonzalez Hernandez, “An interpretable natural language processing system for written medical examination assessment,” J. Biomed. Inform., 2019, doi: 10.1016/j.jbi.2019.103268. [9] T. Noraset, L. Lowphansirikul, and S. Tuarob, “WabiQA: A Wikipedia-Based Thai Question-Answering System,” Inf. Process. Manag., 2021, doi: 10.1016/j.ipm.2020.102431.
D. N. A. Akash Roshan and Meenu Garg, “Intelligent Voice Assisstant for Desktop using NLP and AI,” Int. J. Mod. Trends Sci. Technol., 2020, doi: 10.46501/ijmtst061261.
C. T. Wolf and J. L. Blomberg, “Evaluating the promise of human-algorithm collaborations in everyday work practices,” Proc. ACM Human-Computer Interact., 2019, doi: 10.1145/3359245.
D. Tafazoli, María, E. G. Parra, and C. A. H. Abril, “Intelligent language tutoring system: Integrating intelligent computer-assisted language learning into language education,” Int. J. Inf. Commun. Technol. Educ., 2019, doi: 10.4018/IJICTE.2019070105.
R. Furlan et al., “A natural language processing-based virtual patient simulator and intelligent tutoring system for the clinical diagnostic process: Simulator development and case study,” JMIR Med. Informatics, 2021, doi:
2196/24073.
Q. Li and J. Liu, “Development of An Intelligent NLP Based Audit Plan Knowledge Discovery System,” J. Emerg. Technol. Account., 2019, doi: 10.2308/jeta-19-03- 31-16.
A. N. Mathew, V. Rohini, and J. Paulose, “NLP-based personal learning assistant for school education,” Int. J. Electr. Comput. Eng., 2021, doi: 10.11591/ijece.v11i5.pp4522-4530.
M. H. Chao, A. J. C. Trappey, and C. T. Wu, “Emerging Technologies of Natural Language-Enabled Chatbots: A Review and Trend Forecast Using Intelligent Ontology Extraction and Patent Analytics,” Complexity. 2021, doi: 10.1155/2021/5511866.
N. J. Oscar Hong, U. H. Govindarajan, Y. C. Jack Chang Chien, and J. C. Amy Trappey, “Comprehensive technology function product matrix for intelligent chatbot patent mining,” Conf. Proc. - IEEE Int. Conf. Syst. Man Cybern., vol. 2019-October, pp. 1344–1348, 2019, doi: 10.1109/SMC.2019.8914365.
J. Lester, K. Branting, and B. Mott, “Conversational agents: The practical handbook of internet computing,” Pract. Handb. Internet Comput., pp. 220–240, 2004.
S. Ayanouz, B. A. Abdelhakim, and M. Benhmed, “A Smart Chatbot Architecture based NLP and Machine Learning for Health Care Assistance,” PervasiveHealth Pervasive Comput. Technol. Healthc., 2020, doi: 10.1145/3386723.3387897.
