OPEN SOURCE CHATBOT DEVELOPMENT FRAMEWORK - RASA

PDF

Published: 2022-03-02

Page: 451-453


J. PRAVEEN GUJJAR *

CMS Business School, Jain (Deemed-to-be University), Bengaluru, Karnataka, India.

V. NAVEEN KUMAR

CMS Business School, Jain (Deemed-to-be University), Bengaluru, Karnataka, India.

*Author to whom correspondence should be addressed.


Abstract

Deep learning techniques which implement deep neural networks became popular due to the increase of high-performance computing facility. Deep learning achieves higher power and flexibility due to its ability to process a large number of features when it deals with unstructured data. Deep learning algorithm passes the data through several layers; each layer is capable of extracting features progressively and passes it to the next layer. Initial layers extract low-level features, and succeeding layers combines features to form a complete representation. Chatbot is referred as learning and assistant tool. It is artificially created with the help of neural network in deep learning model. Chatbot is capable enough to interact with the users in the form of text or speech. This paper focuses on the development of chatbot using the open source framework called rasa. Chatbot is a conversational bot which is going to use of natural language processing and mimic the conversation with customer or the users. Rasa has two important component rasa nlu and rasa nlu core. These two are considered as the building block of rasa chatbot. In this article interactive learning and implementation details are tested in anaconda framework. For the implementation purpose rasa 2.0 is used.

Keywords: Hysterothylacium karanensis n.sp., Artificial intelligence, nematode, deep learning, Anisakidae, chatbot, body cavity, NLU, Scoliodon palasorrah (Cuvier), Rasa, Visakhapatnam.


How to Cite

GUJJAR, J. P., & KUMAR, V. N. (2022). OPEN SOURCE CHATBOT DEVELOPMENT FRAMEWORK - RASA. Asian Journal of Advances in Research, 5(1), 451–453. Retrieved from https://jasianresearch.com/index.php/AJOAIR/article/view/406

Downloads

Download data is not yet available.

References

Mondal, Anupam, et al. Chatbot: An automated conversation system for the educational domain. 2018 International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP). IEEE. 2018;1-5.

Bocklisch T, Faulkner J, Pawlowski N, Nichol A. Rasa: Open source language understanding and dialogue management; 2017. arXiv preprint arXiv:1712.05181

Lacerda ARTD. Rasa-ptbr-boilerplate: FLOSS project that enables brazilianportuguese chatbot development by non-experts; 2019.

Jiao A. An intelligent chatbot system based on entity extraction using RASA NLU and neural network. JPhCS. 2020;1487(1):012014.

Singh A, Ramasubramanian K, Shivam S. Introduction to microsoft Bot, RASA, and google dialogflow. In Building an Enterprise Chatbot. Apress, Berkeley, CA. 2019;281-302.

Rakesh Kumar Sharma, and Manoj Joshi. An analytical study and review of open source chatbot framework, RASA, International Journal of Engineering Research & Technology (IJERT). 2020;9(6):1011-1014.

Frommert C, Häfner A, Friedrich J, Zinke C. Using chatbots to assist communication in collaborative networks. In Working Conference on Virtual Enterprises. Springer, Cham. 2018;257-265.

Segura C, Palau A, Luque J, Costa-Jussà MR, Banchs RE. Chatbol, a chatbot for the Spanish “La Liga”. In 9th International Workshop on Spoken Dialogue System Technology. Springer, Singapore. 2019;319-330.

Praveen Gujjar, Prasanna Kumar HR, Niranjan N Chiplunkar. Image classification and prediction using transfer learning in colab notebook. Global Transitions Proceedings. 2021;2(2):382-385.

Praveen Gujjar and Naveen Kumar. google colaboratory: tool for deep learning and machine learning applications. Indian Journal of Computer Science. 2021;6(4):23-26.

Hinton G, Srivastava N, Swersky K. Neural networks for machine learning; 2020.

Available:http://www.cs.toronto.edu/~hinton/coursera/lecture6/lec6.pdf