An Adaptive Conversational Bot Framework

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. Consider the problem of recommending movies to users: it is a longstanding problem in data science that has implied a variety of techniques [1][2], ranging from Conditional Random Fields (for language understanding) to Collaborative Filtering techniques (for recommendation based on users' feedback on watched movies).