Conversational Interfaces for Information Search

Abstract

Recent progress in machine learning has given rise to a plethora of tools and applications that rely on conversational interactions, from chatbots, speech-controlled devices to robots and virtual agents. Conversational interfaces are becoming widely accepted for utility tools, where a common function is to serve users’ information needs. Albeit with much excitement, we are only starting to understand how users’ information-seeking behaviors and design opportunities may transform moving from traditional graphical user interfaces to conversational user interfaces. In this chapter, we start by reviewing recent work in the emerging area of conversational interfaces and lay out their opportunities for supporting information search tasks. We then present insights from our experience deploying a chatbot supporting information search in a large enterprise, demonstrating how a conversational interface impacts user behaviors and offers new opportunities for improving search experience, in particular for user modeling.