A Conceptual IR Chatbot Framework with Automated Keywords-based Vector Representation Generation

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.