Towards a model for spoken conversational search

Abstract

Conversation is the natural mode for information exchange in daily life, a spoken conversational interaction for search input and output is a logical format for information seeking. However, the conceptualisation of user-system interactions or information exchange in spoken conversational search (SCS) has not been explored. The first step in conceptualising SCS is to understand the conversational moves used in an audio-only communication channel for search. This paper explores conversational actions for the task of search. We define a qualitative methodology for creating conversational datasets, propose analysis protocols, and develop the SCSdata. Furthermore, we use the SCSdata to create the first annotation schema for SCS: the SCoSAS, enabling us to investigate interactivity in SCS. We further establish that SCS needs to incorporate interactivity and pro-activity to overcome the complexity that the information seeking process in an audio-only channel poses. In summary, this exploratory study unpacks the breadth of SCS. Our results highlight the need for integrating discourse in future SCS models and contributes the advancement in the formalisation of SCS models and the design of SCS systems.

How Am I Doing?: Evaluating Conversational Search Systems Offline

“…Hence, a possible extension of this approach could be the introduction of a system's persistence similar to the concept of user's persistence. This would be in line with the notion of pro-activity of conversational search systems as suggested by Trippas et al [40].…”

“…These datasets were further followed by some other domain specific conversational datasets [32,44]. Trippas et al [40] defined a method for creating conversational datasets (which could serve as a guide in constructing such datasets) and used that for building one such dataset.…”

Accessing Media Via an Audio-only Communication Channel: A Log Analysis

“…Thus, the infinite-reading mode would continue reading the document titles until a user interrupts the system. Furthermore, enabling users to navigate more freely will inform them which documents are available in the "information space" [14,15]. Two thirds (66.37%) of the one-interaction sessions shown in Table 3 can be interpreted as good abandonment.…”

Towards Multi-Modal Conversational Information Seeking

“…Recent conversational approaches to finding information through dialogue have mainly been viewed from natural language interactions (i.e., search in which input and output are mediated via "conversations" [33,51,60]). Even though several mentions towards conversational multi-modal systems suggested an expansion in the in-and output options [28,46], limited research has been devoted to interacting with IS systems in a range of modalities which complement each other.…”

“…We use the notion of "conversation" as an information exchange with more than two turns instead of commands such as setting a timer or turning on the light. Furthermore, we focus on the topical transactional role of search versus the social chit-chat [9,60]. Despite the growing interest in making everything "conversational", little work has focused on establishing how conversational search interactions can be used in a multi-modal system.…”