A Conceptual Framework for Conversational Search and Recommendation: Conceptualizing Agent-Human Interactions During the Conversational Search Process

While past work has started to tease out different actions that users and agents The conversational search task aims to enable a user to resolve perform and respond to during the conversational search process, information needs via natural language dialogue with there has been little work on formalizing these actions an agent. In this paper, we aim to develop a conceptual and decisions. Thus the goal of this paper is to develop a framework of the actions and intents of users and agents conceptual framework of different actions and intents, along explaining how these actions enable the user to explore the with the key decision points within the conversation. Our search space and resolve their information need. We outline aim is to make these tasks explicit in order to formalize the different actions and intents, before discussing key decision the research, development and evaluation of conversational points in the conversation where the agent needs to search agents. To this end, we first examine the key actions decide how to steer the conversational search process to a successful and intents identified in past work, and enumerate these and/or satisfactory conclusion. Essentially, this paper along with others that can be naturally inferred from a simulated provides a conceptualization of the conversational search process conversational context, before discussing the key decisions between an agent and user, which provides a framework that the agent needs to make in order to advance the and a starting point for research, development and evaluation conversation to a satisfactory or successful end. of conversational search agents.