STUDENT INFORMATION AI CHATBOT
Main Article Content
Abstract
-Automatic conversation system is an intelligent human machine interaction using natural language. Main goal of it is to allow the user and machine to make a natural harmonious conversation. Thus enabling the machine to recognize human motivation and to respond accurately, is not only an important manifestation of advanced intelligence, but also a very challenging work in harmonious human interaction field [1]. A conversation system consists of speech recognition, speech synthesis, and dialogue management and conversation generation. In this research, we focus on automatic generation of conversation between a computer and a human being with little knowledge of the computer.In this paper, we influenced a PC to end up a preparation to accomplice of a man who isn't great at discussion, to wind up a band together with a man. Therefore, in this research, we are focusing specifically on “chat" by developing an interactive AI which converse mainly by using machine learning. We perform a word unit prediction by using “Hill Climbing†algorithm and based on relevancy ranking, the relevant conversation is made.Our main focus, is to build a Student chat bot which helps the colleges to have 24*7 automated query resolution. This helps the students to have the right information from the trusted source. Also the administrationof information is made easy for the institutions.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.
References
I. A. I. Lopatovska, "Theories, methods and current research on emotions in library and information science, information retrieval and human computer interaction," Information Processing and Management, pp. 575 592, 2011, vol. 47. [2] Ilya Sutskever, Oriol Vinyals, Quoc V. Le:, Sequence to sequence learning with neural networks, pp. 3104-3112, NIPS 2014. [3] Oriol Vinyals, Quoc V. Le: A neural conversational model, pp. 211-225 ACL 2015. [4] Kaoru Nasuno Yutaka Matsuo, "Generating a reply on Twitter using a neural conversational model," pp. 851-870,The 30th AnnualConference of the Japanese Society for Artificial Intelligence, 2016. [5] Ryan Lowe, Nissan Pow, Iulian Serban, Joelle Pineau, “The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi- Turn Dialogue Systemsâ€, pp. 285-294, SIGDIAL 2015. [6] Rudolf Kadlec, Martin Schmid, Jan Kleindienst, “Improved Deep Learning Baselines for Ubuntu Corpus Dialogsâ€, Machine Learning for SLU & Interaction, pp. 348-383, NIPS 2015 Workshop, 2015. [7] Lifeng Shang, Zhengdong Lu, Hang Li, “Neural Responding Machine for Short-Text Conversationâ€, pp. 1577-1586, ACL 2015.. [8] Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, “A Neural Network Approach to Context-Sensitive Generation of Conversational Responsesâ€,pp. 196-205, NAACL-HLT 2015. [9] Kaisheng Yao, Geoffrey Zweig, Baolin Peng, “Attention with Intention for a Neural Network Conversation Modelâ€, pp. 1183-1193, NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction. 2015.