A conceptual IR Chatbot framework with automated keywords-based vector representation generation

Abbas Saliimi, Lokman and M. A., Ameedeen and Ngahzaifa, Ab. Ghani (2020) A conceptual IR Chatbot framework with automated keywords-based vector representation generation. In: IOP Conference Series: Materials Science and Engineering, The 6th International Conference on Software Engineering & Computer Systems , 25-27 September 2019 , Pahang, Malaysia. pp. 1-9., 769 (012020). ISSN 1757-8981 (Print); 1757-899X (Online)

[img]
Preview
Pdf
A conceptual ir chatbot framework with Automated Keywords.pdf
Available under License Creative Commons Attribution.

Download (435kB) | Preview

Abstract

This paper proposes a conceptual remodel of Information Retrieval (IR) chatbot framework designed to eliminate the need for large Question-Answer (QA) pair dataset in chatbot's machine learning training and knowledge base development. Within ten proposed framework's components, we describe Ans2Q: a Neural Network model for question type approximation, and HR6: an IR score ranking calculation based on Ans2Q output. Fundamentally, these two components are the variance in which the proposed framework differs from others. Together with process flow explanation, we also provide several related formulas that hopefully can be used to implement this framework. Our general aim with this framework is to provide a tool that can be used to develop close domain chatbot with small knowledge and no readily available QA pair datasets.

Item Type: Conference or Workshop Item (Lecture)
Uncontrolled Keywords: Question-Answer (QA); Information Retrieval (IR); Ans2Q
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computing
Depositing User: Pn. Hazlinda Abd Rahman
Date Deposited: 16 Jun 2020 06:41
Last Modified: 19 Nov 2020 07:50
URI: http://umpir.ump.edu.my/id/eprint/27707
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item