IR with intelligent conversational agents
As access to information becomes more intensive in society, a great deal of that information is becoming available
through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational
agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users
based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that
uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to
support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing
information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an
information retrieval service for websites to verify the usefulness of the proposed method.
Only registered members are allowed to comment.