An Adaptive Conversational Bot Framework

TL;DR

This paper presents a flexible conversational bot framework that dynamically adapts its questioning and information extraction strategies based on user interactions, demonstrated through a movie database query bot.

Contribution

It introduces a novel adaptive framework for conversational bots that improves user experience by customizing interactions based on user behavior and provides implementation techniques.

Findings

Framework effectively adapts to user behavior

Comparison of existing tools highlights novel techniques

Demo bot successfully queries movie database

Abstract

How can we enable users to heavily specify criteria for database queries in a user-friendly way? This paper describes a general framework of a conversational bot that extracts meaningful information from user's sentences, that asks subsequent questions to complete missing information, and that adjusts its questions and information-extraction parameters for later conversations depending on users' behavior. Additionally, we provide a comparison of existing tools and give novel techniques to implement such framework. Finally, we exemplify the framework with a bot to query movies in a database, whose code is available for Microsoft employees.