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

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...

Full description

Bibliographic Details
Main Authors: Abbas Saliimi, Lokman, M. A., Ameedeen, Ngahzaifa, Ab. Ghani
Format: Conference or Workshop Item
Language:English
Published: IOP Publishing 2020
Subjects:
Online Access:http://umpir.ump.edu.my/id/eprint/27707/13/A%20conceptual%20ir%20chatbot%20framework%20with%20Automated%20Keywords.pdf
_version_ 1825813218016100352
author Abbas Saliimi, Lokman
M. A., Ameedeen
Ngahzaifa, Ab. Ghani
author_facet Abbas Saliimi, Lokman
M. A., Ameedeen
Ngahzaifa, Ab. Ghani
author_sort Abbas Saliimi, Lokman
collection UMP
description 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.
first_indexed 2024-03-06T12:40:44Z
format Conference or Workshop Item
id UMPir27707
institution Universiti Malaysia Pahang
language English
last_indexed 2024-03-06T12:40:44Z
publishDate 2020
publisher IOP Publishing
record_format dspace
spelling UMPir277072020-11-19T07:50:41Z http://umpir.ump.edu.my/id/eprint/27707/ A conceptual IR Chatbot framework with automated keywords-based vector representation generation Abbas Saliimi, Lokman M. A., Ameedeen Ngahzaifa, Ab. Ghani QA76 Computer software 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. IOP Publishing 2020 Conference or Workshop Item PeerReviewed pdf en cc_by http://umpir.ump.edu.my/id/eprint/27707/13/A%20conceptual%20ir%20chatbot%20framework%20with%20Automated%20Keywords.pdf 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) (Published) https://doi.org/10.1088/1757-899X/769/1/012020
spellingShingle QA76 Computer software
Abbas Saliimi, Lokman
M. A., Ameedeen
Ngahzaifa, Ab. Ghani
A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title_full A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title_fullStr A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title_full_unstemmed A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title_short A conceptual IR Chatbot framework with automated keywords-based vector representation generation
title_sort conceptual ir chatbot framework with automated keywords based vector representation generation
topic QA76 Computer software
url http://umpir.ump.edu.my/id/eprint/27707/13/A%20conceptual%20ir%20chatbot%20framework%20with%20Automated%20Keywords.pdf
work_keys_str_mv AT abbassaliimilokman aconceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration
AT maameedeen aconceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration
AT ngahzaifaabghani aconceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration
AT abbassaliimilokman conceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration
AT maameedeen conceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration
AT ngahzaifaabghani conceptualirchatbotframeworkwithautomatedkeywordsbasedvectorrepresentationgeneration