An Adaptive Conversational Bot Framework
This addresses the challenge of making database queries more user-friendly for general users, though it appears incremental by building on existing conversational bot techniques.
The paper tackles the problem of enabling users to specify complex database query criteria through a conversational bot framework that extracts information, asks follow-up questions, and adapts based on user behavior, demonstrating it with a movie database bot available to Microsoft employees.
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.