Towards Human-Like Conversational Search Systems

Abstract

Voice search is currently widely available on the majority of mobile devices via use of Virtual Personal Assistants. However, despite its general availability, the use of voice interaction remains sporadic and is limited to basic search tasks such as checking weather updates and looking up answers to factual queries. Present-day voice search systems struggle to use relevant contextual information to maintain conversational state, and lack conversational initiative needed to clarify user's intent, which hampers their usability and prevents users from engaging in more complex interaction activities. This research investigates the potential of a hypothesised interactive information retrieval system with human-like conversational abilities. To this end, we propose a series of usability studies that involve a working prototype of a conversational system that uses real time speech synthesis. The proposed experiments seek to provide empirical evidence that enabling a voice search system with human-like conversational abilities can lead to increased likelihood of its adoption.